© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6401
    Prev
    Next
    INDEX
    Explanations

    code-related words

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Ra
    -0.47
    ården
    -0.47
     log
    -0.47
     пы
    -0.46
    eqref
    -0.45
    CultureInfo
    -0.44
    рави
    -0.44
    aud
    -0.43
    imo
    -0.43
     gathering
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.69
     InputDecoration
    0.66
    onAttach
    0.66
     vectorielle
    0.66
     Strike
    0.63
     Kern
    0.60
    openConnection
    0.60
     Basta
    0.59
    WireFormatLite
    0.59
    tagez
    0.58
    Activations Density 6.945%

    No Known Activations