© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144177
    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_0_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
    be
    0.58
    en
    0.57
    ang
    0.57
     organis
    0.56
    Pada
    0.56
    Linux
    0.55
     a
    0.55
    Te
    0.54
    te
    0.54
    Be
    0.54
    POSITIVE LOGITS
    투자
    0.47
     செல்சிய
    0.46
     கெல்
    0.46
    숄
    0.46
    شون
    0.45
     wrongs
    0.45
    ومان
    0.45
     Correlations
    0.45
     khoan
    0.44
     ப்ளாக்
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.