© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60932
    Prev
    Next
    INDEX
    Explanations

    addressing concerns

    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_11_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
    ط
    0.56
    ง
    0.52
     $
    0.45
    การ
    0.44
    lang
    0.44
     sciences
    0.44
    个
    0.44
    ra
    0.43
    eers
    0.43
    Т
    0.43
    POSITIVE LOGITS
    M
    0.48
     Ejec
    0.48
    FOUR
    0.48
    {,}
    0.48
    Ek
    0.47
    欤
    0.47
    इस
    0.46
    DEBUGFS
    0.46
    P
    0.46
     milites
    0.46
    Activations Density 0.008%

    No Known Activations