© 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. 206228
    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
    m
    1.05
    <0x0D>
    0.93
    tte
    0.90
     you
    0.87
    ening
    0.86
    v
    0.84
    ark
    0.82
     an
    0.81
    ilt
    0.77
    aste
    0.77
    POSITIVE LOGITS
    و
    1.24
    Y
    1.19
    P
    1.12
    كا
    1.09
    R
    1.08
    Type
    1.06
    Czas
    1.06
    Pasta
    1.06
    יי
    1.04
    Paint
    1.04
    Activations Density 0.000%

    No Known Activations