© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2790
    Prev
    Next
    INDEX
    Explanations

    sentences that describe features and functionality relating to user interfaces and mechanical devices in extreme detail.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and UI elements

    np_token-act-pair-logits · gpt-4o-mini

    UI features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.74
     Paglinawan
    -0.65
     ब्रेकडाउन
    -0.58
    SaveChangesAsync
    -0.58
    getDoctrine
    -0.54
    tagHelperRunner
    -0.52
     betweenstory
    -0.52
     SEDS
    -0.51
     gout
    -0.50
     étoient
    -0.50
    POSITIVE LOGITS
    migrationBuilder
    0.63
     Rock
    0.60
     rock
    0.58
     snippetHide
    0.55
     Slide
    0.54
     pull
    0.52
    GraphicsUnit
    0.51
    Personendaten
    0.51
    acherous
    0.51
    LayoutConstraint
    0.51
    Activations Density 2.890%

    No Known Activations