© 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. 865
    Prev
    Next
    INDEX
    Explanations

    words and phrases that commonly occur in formal legal or scientific arguments.

    oai_token-act-pair · gemini-2.0-flash

    Someone speaking or arguing

    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
     states
    -0.94
    Says
    -0.88
     States
    -0.84
     note
    -0.83
    says
    -0.82
     Says
    -0.76
     STATES
    -0.76
    states
    -0.72
     mentions
    -0.72
     notes
    -0.71
    POSITIVE LOGITS
    GraphicsUnit
    0.66
    InjectAttribute
    0.60
    UnusedPrivate
    0.57
     onCancelled
    0.56
    HtmlAttribute
    0.56
     kaynağından
    0.55
     endforeach
    0.53
    FORMANCE
    0.53
    зможно
    0.52
    moveToFirst
    0.52
    Activations Density 4.091%

    No Known Activations