© 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. 6586
    Prev
    Next
    INDEX
    Explanations

    section headers and references to legal code

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    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
    Rails
    -0.42
     francia
    -0.37
    got
    -0.35
     dark
    -0.35
     Dark
    -0.35
     cool
    -0.34
    dark
    -0.34
    宿
    -0.34
    unload
    -0.34
    PrototypeOf
    -0.33
    POSITIVE LOGITS
     tartalomajánló
    0.89
    ArgsConstructor
    0.77
    RenderAtEndOf
    0.74
    Hochspringen
    0.73
    DeleteBehavior
    0.73
    WriteBarrier
    0.71
    afficheront
    0.69
    WithIOException
    0.66
    ніципалі
    0.66
    CodeAttribute
    0.65
    Activations Density 37.332%

    No Known Activations