© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35229
    Prev
    Next
    INDEX
    Explanations

    long predicted or believed

    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_7_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
    et
    0.94
     Ā
    0.91
    Perform
    0.87
    𝐒
    0.86
    م
    0.85
     BUT
    0.84
    이지만
    0.84
     AND
    0.84
    Margins
    0.83
    ق
    0.83
    POSITIVE LOGITS
    ль
    0.85
     complained
    0.84
    in
    0.77
    ߋ
    0.75
    п
    0.75
     fino
    0.74
     cabeza
    0.73
    દ
    0.73
     gewoon
    0.73
     comforting
    0.72
    Activations Density 0.004%

    No Known Activations