© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197304
    Prev
    Next
    INDEX
    Explanations

    star or stars

    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_4_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
    ل
    1.15
    ,
    1.02
    ip
    1.00
    ิ
    0.96
    ం
    0.91
    io
    0.91
    ics
    0.90
    herent
    0.89
    ้
    0.88
    ut
    0.85
    POSITIVE LOGITS
    き
    0.98
     (
    0.95
    ש
    0.95
    ྥ
    0.83
    जून
    0.81
     قیامت
    0.80
     C
    0.79
     מ
    0.79
     болезнь
    0.78
    个
    0.78
    Activations Density 0.000%

    No Known Activations