© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6592
    Prev
    Next
    INDEX
    Explanations

    bits of Javascript code, particularly those using the $ and # symbols, likely in relation to jQuery

    oai_token-act-pair · gemini-2.0-flash

    $("#

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Monfieur
    -1.65
     Efq
    -1.62
     Reſ
    -1.61
     Theſe
    -1.59
     Anſ
    -1.54
     Eſ
    -1.53
     Houſe
    -1.45
     Diſ
    -1.41
     Beſ
    -1.40
     Jefus
    -1.38
    POSITIVE LOGITS
     an
    0.76
     and
    0.75
     the
    0.72
     '
    0.70
     a
    0.70
     var
    0.69
     I
    0.67
     P
    0.67
     M
    0.67
     S
    0.67
    Activations Density 0.910%

    No Known Activations