© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206572
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    у
    0.90
    US
    0.88
    り
    0.83
    ച്
    0.82
    Р
    0.79
    У
    0.77
     عنها
    0.76
    вав
    0.75
     عنه
    0.74
    IS
    0.73
    POSITIVE LOGITS
    s
    2.14
    in
    1.27
    \
    1.18
    y
    1.17
    to
    1.16
    ra
    1.14
    sü
    1.12
    ের
    1.09
    ség
    1.08
    m
    1.04
    Activations Density 0.000%

    No Known Activations