© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9547
    Prev
    Next
    INDEX
    Explanations

    code snippets including css styles

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     avoit
    -0.65
     auroit
    -0.59
     pouvoit
    -0.59
     étoit
    -0.58
     getattr
    -0.57
    interopRequire
    -0.56
    $.
    -0.56
     économiques
    -0.55
     avoient
    -0.55
     étn
    -0.55
    POSITIVE LOGITS
    jgl
    0.65
     programme
    0.61
     Programme
    0.60
    IntoConstraints
    0.57
     Programmes
    0.57
    programme
    0.56
     GenerationType
    0.56
     estekak
    0.55
     programmes
    0.55
     []:
    0.55
    Activations Density 0.088%

    No Known Activations