© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12120
    Prev
    Next
    INDEX
    Explanations

    Java code syntax and structure

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     protoimpl
    -0.82
    <?
    -0.75
     wireType
    -0.73
    Дереккөздер
    -0.69
    ngrx
    -0.69
     oprot
    -0.69
    contentLoaded
    -0.66
    uxxxx
    -0.66
     AssemblyCulture
    -0.64
    eload
    -0.63
    POSITIVE LOGITS
     NDEBUG
    0.56
    σαι
    0.51
    getFirstName
    0.48
    getLastName
    0.48
    ORETICAL
    0.46
    CancelButton
    0.46
    Recher
    0.45
    setFirstName
    0.45
     Sto
    0.44
    голо
    0.44
    Activations Density 16.660%

    No Known Activations