© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194255
    Prev
    Next
    INDEX
    Explanations

    immediately recognizable

    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_9_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
    -
    0.82
    ’
    0.64
    '
    0.62
    \
    0.55
    ");
    0.54
    _
    0.53
    PE
    0.52
    ’;
    0.51
    CIÓN
    0.51
    UT
    0.50
    POSITIVE LOGITS
    ع
    0.85
    м
    0.66
    س
    0.66
    م
    0.63
    но
    0.61
    ق
    0.61
    ی
    0.60
    е
    0.59
    ่า
    0.57
    ம்
    0.57
    Activations Density 0.020%

    No Known Activations