© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139554
    Prev
    Next
    INDEX
    Explanations

    San followed by names

    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_12_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
    عمل
    0.54
    쿠
    0.54
    NAME
    0.53
    여자
    0.51
     działal
    0.51
    نساء
    0.50
    莳
    0.49
    UTF
    0.49
    GetService
    0.49
    도
    0.49
    POSITIVE LOGITS
    elia
    0.54
    st
    0.53
     šť
    0.52
    atrice
    0.50
    buffers
    0.50
    ición
    0.50
    ariya
    0.49
     calculus
    0.49
     unimagin
    0.49
    肃
    0.48
    Activations Density 0.000%

    No Known Activations