© 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. 38121
    Prev
    Next
    INDEX
    Explanations

    guidelines, details, and what follows

    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
     that
    0.92
    3
    0.92
    1
    0.91
    ה
    0.86
    া
    0.83
    ه
    0.80
    は
    0.80
    -
    0.79
    是
    0.75
    ा
    0.73
    POSITIVE LOGITS
    c
    1.11
    g
    0.88
    k
    0.82
    ين
    0.80
    b
    0.78
    d
    0.68
    dT
    0.67
    cD
    0.67
    cB
    0.66
    el
    0.66
    Activations Density 0.019%

    No Known Activations