© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134575
    Prev
    Next
    INDEX
    Explanations

    sign or age

    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_6_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
    '
    1.02
    のは
    0.92
     പോലും
    0.92
     Hesap
    0.92
     Çalış
    0.90
     İş
    0.89
    인을
    0.89
     Öğ
    0.89
    Від
    0.89
     Doğ
    0.88
    POSITIVE LOGITS
    us
    1.05
     (
    0.91
    in
    0.89
     moistur
    0.88
    ור
    0.86
    ot
    0.85
    ى
    0.84
    س
    0.83
     utilization
    0.82
     summar
    0.82
    Activations Density 0.001%

    No Known Activations