© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203933
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ça
    0.36
    갤
    0.34
     unap
    0.33
     közé
    0.33
     XXL
    0.32
    0.32
    //
    0.32
     сё
    0.32
     frontière
    0.32
     vle
    0.32
    POSITIVE LOGITS
    ,.
    0.41
    :.
    0.39
    deviation
    0.36
    },
    0.35
    mlin
    0.35
    INC
    0.34
    .}
    0.34
     Brunch
    0.34
    :}
    0.33
    ilir
    0.33
    Activations Density 0.002%

    No Known Activations