© 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. 351
    Prev
    Next
    INDEX
    Explanations

    descriptions of things being blocked or not working, as well as descriptions of being sick

    oai_token-act-pair · gemini-2.0-flash

    negative situations

    np_max-act-logits · 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
    tagHelperRunner
    -0.81
    UnusedPrivate
    -0.69
    MigrationBuilder
    -0.67
    IsMutable
    -0.67
    InjectAttribute
    -0.65
    Personensuche
    -0.64
     للاسماء
    -0.60
    ChildIndex
    -0.60
    iddhartha
    -0.59
     ens
    -0.59
    POSITIVE LOGITS
    stdc
    0.47
     Punch
    0.45
    ArgsConstructor
    0.44
     dépens
    0.44
     abstrait
    0.43
     débats
    0.42
     recevrez
    0.42
     مُعرِّف
    0.42
     leçons
    0.42
     punch
    0.41
    Activations Density 2.426%

    No Known Activations