© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122493
    Prev
    Next
    INDEX
    Explanations

    special characters and code delimiters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ledon
    0.85
     for
    0.84
    Ყ
    0.79
    inama
    0.76
    inį
    0.74
    咟
    0.73
    িদ্ধ
    0.72
    herlands
    0.71
     Than
    0.71
    ড়যন্ত্র
    0.71
    POSITIVE LOGITS
    م
    1.20
    м
    1.18
    v
    1.17
    l
    1.06
    j
    0.97
    r
    0.96
    </strong>
    0.95
    b
    0.92
     a
    0.91
    ។
    0.91
    Activations Density 0.053%

    No Known Activations