© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10448
    Prev
    Next
    INDEX
    Explanations

    you shall not

    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_40_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
    roffenen
    0.45
     termini
    0.38
    +"','"+
    0.37
     BOOKS
    0.36
    žete
    0.36
    ிற்
    0.36
    പ്പം
    0.36
    uruan
    0.35
    lemm
    0.35
     inviol
    0.35
    POSITIVE LOGITS
     无
    0.37
    恐
    0.37
     yas
    0.36
    🇨
    0.36
     ক্রিকেট
    0.36
     Western
    0.36
     Mé
    0.36
     Lup
    0.36
    Source
    0.35
    Assembly
    0.35
    Activations Density 0.000%

    No Known Activations