© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11787
    Prev
    Next
    INDEX
    Explanations

    technical terminology about bicycle parts and maintenance

    oai_token-act-pair · gemini-2.0-flash

    bicycle parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ="">
    -0.64
    __':
    -0.63
     revenus
    -0.54
     ){
    -0.54
    aarrggbb
    -0.54
    '">
    -0.53
    )*/
    -0.52
     meubles
    -0.51
     الحره
    -0.51
     {
    -0.50
    POSITIVE LOGITS
    UrlResolution
    0.66
    новниш
    0.66
    Uninitialized
    0.55
    rawQuery
    0.55
    DockStyle
    0.50
    BufferException
    0.50
     SqlCommand
    0.49
     gynhyrchwyd
    0.48
     MainAxisSize
    0.47
    참고
    0.47
    Activations Density 1.500%

    No Known Activations