© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86925
    Prev
    Next
    INDEX
    Explanations

    room, IP, cake, fish, flies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    𝘱
    0.71
    ların
    0.70
    dı
    0.67
    bff
    0.66
    d
    0.66
    to
    0.65
    drive
    0.65
    daily
    0.64
    dry
    0.63
    tochy
    0.63
    POSITIVE LOGITS
    ő
    0.76
    وني
    0.75
    ية
    0.69
     vacances
    0.67
    ב
    0.66
    il
    0.66
    hurst
    0.64
    -
    0.64
    т
    0.64
    ieurs
    0.63
    Activations Density 0.000%

    No Known Activations