© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200538
    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
    </h2>
    0.91
    ↵↵
    0.90
    는
    0.89
    <0x0D>
    0.80
     Scalars
    0.79
    </b>
    0.75
    <h2>
    0.74
    0.74
    !’
    0.73
    ippings
    0.73
    POSITIVE LOGITS
    on
    1.24
    B
    1.23
    W
    1.10
    X
    1.08
    G
    1.03
    R
    1.02
    J
    0.99
    S
    0.97
    T
    0.95
    ால்
    0.95
    Activations Density 0.000%

    No Known Activations