© 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. 3192
    Prev
    Next
    INDEX
    Explanations

    code syntax, particularly code that includes square brackets, colons, and parentheses

    oai_token-act-pair · gemini-2.0-flash

    brackets/parenthesis

    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
    WithIOException
    -0.86
    oredCriteria
    -0.73
    webElementXpaths
    -0.73
    таратура
    -0.73
    ThroughAttribute
    -0.70
    Personensuche
    -0.69
    OGND
    -0.67
     gynhyrchwyd
    -0.64
     InputDecoration
    -0.63
    .’”
    -0.63
    POSITIVE LOGITS
    '
    0.53
    '">
    0.51
    ært
    0.48
    ிறது
    0.46
    ობ
    0.45
    zuführen
    0.44
     refreshing
    0.44
     Estadística
    0.44
     aman
    0.44
    ัติ
    0.44
    Activations Density 5.158%

    No Known Activations