© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15265
    Prev
    Next
    INDEX
    Explanations

    personal pronouns ("I", "he", "she") or names of people.

    oai_token-act-pair · gemini-2.0-flash

    personal expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     חיצוניים
    -0.73
     hänen
    -0.65
    Демографія
    -0.59
    AccessorTable
    -0.59
     незавершена
    -0.57
    Билгалдахарш
    -0.56
    Autoritní
    -0.56
    Aholisi
    -0.55
     ModelExpression
    -0.55
    <bos>
    -0.55
    POSITIVE LOGITS
     own
    0.52
     adored
    0.50
    ubourg
    0.48
    分ほど
    0.47
    ISB
    0.47
    hores
    0.46
     Dowling
    0.46
    ême
    0.46
    IActionResult
    0.46
    自己的
    0.45
    Activations Density 21.803%

    No Known Activations