© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135025
    Prev
    Next
    INDEX
    Explanations

    how much does it cost

    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_37_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
     יכול
    0.42
     ډاونلوډ
    0.42
    份
    0.39
    误差
    0.38
     제곱
    0.37
     नाइट्र
    0.37
     ক্রয়
    0.37
     PURCHASE
    0.37
    辗
    0.37
    身長
    0.36
    POSITIVE LOGITS
    gee
    0.40
    btree
    0.39
    el
    0.37
    innon
    0.37
     влади
    0.36
     ger
    0.36
    жений
    0.36
     ep
    0.36
    ecer
    0.35
    elingen
    0.35
    Activations Density 0.002%

    No Known Activations