© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16163
    Prev
    Next
    INDEX
    Explanations

    various symbols and keywords common in Javascript code

    oai_token-act-pair · gemini-2.0-flash

    dot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     JpaRepository
    -0.71
    AsUp
    -0.70
    المكان
    -0.68
    AndroidJUnit
    -0.68
    SourceChecksum
    -0.68
    NameInMap
    -0.66
    VIAF
    -0.66
     ivelany
    -0.65
     Италијани
    -0.63
    ագրություններ
    -0.63
    POSITIVE LOGITS
    addEventListener
    0.47
     contactez
    0.46
    pg
    0.41
     ipsum
    0.41
    saludos
    0.40
     Ilmu
    0.40
    glyphicon
    0.40
    ep
    0.39
    toThrow
    0.39
    nout
    0.38
    Activations Density 1.545%

    No Known Activations