© 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. 127461
    Prev
    Next
    INDEX
    Explanations

    base, olon, hoven

    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
    ين
    0.86
    ח
    0.84
     eind
    0.69
    ת
    0.68
     Montpellier
    0.68
    ин
    0.67
     morrer
    0.67
     justific
    0.67
     souten
    0.66
     extinct
    0.65
    POSITIVE LOGITS
    I
    0.78
    o
    0.74
    flake
    0.64
    oC
    0.61
    W
    0.59
    ('_
    0.59
    ozo
    0.59
    Her
    0.58
    ￥
    0.58
     تھے
    0.57
    Activations Density 0.000%

    No Known Activations