© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79653
    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_0_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
     for
    1.74
     at
    1.73
    د
    1.28
    ار
    1.25
     of
    1.21
     the
    1.14
    ח
    1.09
    ोदय
    1.06
     out
    1.05
     hry
    1.05
    POSITIVE LOGITS
    '
    1.96
    ’
    1.66
     I
    1.59
    ك
    1.31
    들이
    1.22
    ׳
    1.19
    로
    1.18
    '*
    1.12
    a
    1.12
    大脑
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.