© 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. 14480
    Prev
    Next
    INDEX
    Explanations

    file paths and numerical versioning

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

    np_token-act-pair-logits · gpt-4o-mini
    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
    ITERATURE
    -0.65
     Theſe
    -0.65
    〢
    -0.63
     المعيارى
    -0.62
     beſt
    -0.61
     tartalomajánló
    -0.60
     voren
    -0.60
    lause
    -0.60
    achusetts
    -0.59
    Cordialement
    -0.59
    POSITIVE LOGITS
    <bos>
    0.53
    bodyParser
    0.51
     “
    0.47
    UnknownFields
    0.47
     Wicidata
    0.47
     "
    0.45
    lor
    0.44
    writeFieldEnd
    0.44
    getItemId
    0.44
     «
    0.44
    Activations Density 0.457%

    No Known Activations