© 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. 15052
    Prev
    Next
    INDEX
    Explanations

    words that describe a natural landscape and its features.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

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

    Technical/Formal writing

    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
     فريبيس
    -0.57
    ClientSize
    -0.51
    fore
    -0.49
    Dr
    -0.46
    nestjs
    -0.45
     []:
    -0.45
     Dr
    -0.45
    älde
    -0.44
    zepine
    -0.44
    不定
    -0.42
    POSITIVE LOGITS
    TestingModule
    0.65
    rungsseite
    0.57
    UnknownFields
    0.56
     Walkover
    0.56
     beginnetje
    0.54
     astore
    0.54
    WireFormatLite
    0.53
    OGND
    0.53
    quels
    0.52
     MenuView
    0.52
    Activations Density 1.016%

    No Known Activations