© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11874
    Prev
    Next
    INDEX
    Explanations

    em dashes

    oai_token-act-pair · gemini-2.0-flash

    em dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    —
    -2.22
    "—
    -1.94
    )—
    -1.89
    ”—
    -1.80
    —"
    -1.80
    !—
    -1.75
    —“
    -1.63
    --
    -1.63
    ?—
    -1.59
    —(
    -1.56
    POSITIVE LOGITS
     «
    1.16
    Â
    1.07
     Ã
    1.03
    `
    0.98
     ->
    0.90
    ･･･
    0.90
     `
    0.88
    Ã
    0.85
    .»
    0.82
     >>
    0.81
    Activations Density 2.083%

    No Known Activations