© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8413
    Prev
    Next
    INDEX
    Explanations

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ɖ
    1.91
    𝘻
    1.79
    й
    1.67
    𝘷
    1.65
    dados
    1.63
    あれば
    1.59
    ில்
    1.57
    ž
    1.57
    льну
    1.51
    𝘵
    1.48
    POSITIVE LOGITS
    <bos>
    1.86
    𝚊
    1.85
     Elaine
    1.85
    ES
    1.83
    ्स
    1.77
     prophylaxis
    1.77
     lamang
    1.75
    𝚎
    1.74
    此之外
    1.73
    రిత్ర
    1.72
    Activations Density 0.011%

    No Known Activations