© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11706
    Prev
    Next
    INDEX
    Explanations

    as much as

    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
     Kitt
    0.30
    瑪
    0.29
     unr
    0.29
    বির
    0.28
    ),
    0.28
    도는
    0.28
     Avion
    0.27
    semb
    0.27
    अ
    0.27
    Mr
    0.26
    POSITIVE LOGITS
    ları
    0.32
     Nếu
    0.31
    ara
    0.31
     pelo
    0.30
     freak
    0.30
     Até
    0.29
    rice
    0.29
     eventuali
    0.28
     terrain
    0.28
     ຫຼື
    0.28
    Activations Density 0.029%

    No Known Activations