© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237838
    Prev
    Next
    INDEX
    Explanations

    showing interest

    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_32_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
    particularly
    0.44
    InCategory
    0.41
     это
    0.38
    惴
    0.38
    までも
    0.38
     КАК
    0.37
    ബ്‌
    0.37
     особенно
    0.36
    加速
    0.36
    %、
    0.36
    POSITIVE LOGITS
     htonl
    0.39
     glycoprotein
    0.38
    ⦕
    0.38
    ﹙
    0.37
    lbrace
    0.37
     changing
    0.36
    人格
    0.36
    atka
    0.36
     \(
    0.35
    avl
    0.35
    Activations Density 0.007%

    No Known Activations