© 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. 8427
    Prev
    Next
    INDEX
    Explanations

    abbreviated words and package names (likely code)

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code-related keywords

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

    code or errors

    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
    WEBPACK
    -0.68
     mon
    -0.47
     share
    -0.46
    ApiModel
    -0.44
     end
    -0.43
     Q
    -0.43
     aim
    -0.41
    قب
    -0.41
     plot
    -0.40
     address
    -0.40
    POSITIVE LOGITS
    Tembelea
    0.99
     nahilalakip
    0.88
    LLocation
    0.77
    GOTREF
    0.76
    ChildScrollView
    0.74
     autorytatywna
    0.74
    ngdoc
    0.73
    djangoproject
    0.73
     ProtoMessage
    0.72
    Демографія
    0.71
    Activations Density 2.106%

    No Known Activations