© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12138
    Prev
    Next
    INDEX
    Explanations

    demanded that

    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_13_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
     भारतात
    0.31
    蟒
    0.30
     COND
    0.27
     ಮಾಡುವ
    0.26
     পাকিস্তানিদের
    0.26
     करण्याचे
    0.26
     жовт
    0.26
     ottenuto
    0.26
    ચર
    0.26
     equivoc
    0.26
    POSITIVE LOGITS
    dealer
    0.31
    est
    0.29
     非
    0.29
    щает
    0.29
    negoti
    0.28
    Dealer
    0.28
    Negoti
    0.28
    非
    0.28
     Non
    0.27
    Studio
    0.27
    Activations Density 0.038%

    No Known Activations