© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121569
    Prev
    Next
    INDEX
    Explanations

    elevator adds

    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
    Negative Logits
    и
    0.82
     mismas
    0.73
     in
    0.72
     mismo
    0.69
     stesse
    0.68
     в
    0.67
     dites
    0.67
     documentaries
    0.66
     stessi
    0.65
    enia
    0.65
    POSITIVE LOGITS
    V
    0.75
    mathbb
    0.74
    </h3>
    0.72
    B
    0.69
    X
    0.68
    Y
    0.66
    Client
    0.64
    dfrac
    0.63
    Bbb
    0.63
    W
    0.63
    Activations Density 0.000%

    No Known Activations