© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11921
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and scientific symbols

    oai_token-act-pair · gemini-2.0-flash

    scientific notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     beginnetje
    -0.79
     jScrollPane
    -0.74
    gonic
    -0.69
    StoryboardSegue
    -0.69
    Parcelize
    -0.63
     Савезне
    -0.60
    TagMode
    -0.60
    AnchorStyles
    -0.59
    migrationBuilder
    -0.58
     चीज़ों
    -0.58
    POSITIVE LOGITS
    ClInclude
    0.49
     p
    0.47
    iento
    0.46
     Prefer
    0.46
    ländische
    0.45
    igeon
    0.44
     Mont
    0.44
     отношений
    0.44
     Christ
    0.43
     CFD
    0.43
    Activations Density 1.267%

    No Known Activations