© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232360
    Prev
    Next
    INDEX
    Explanations

    highly reactive

    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_6_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
    c
    1.34
    s
    1.21
    ,
    1.19
     acumen
    1.07
    n
    0.95
    cji
    0.94
    কে
    0.93
    q
    0.93
    ের
    0.92
    음
    0.92
    POSITIVE LOGITS
     río
    1.01
     Protestant
    0.97
    。
    0.95
    ák
    0.93
     النها
    0.90
     relleno
    0.89
     Viet
    0.88
     Teatro
    0.88
     Não
    0.87
    ？
    0.87
    Activations Density 0.003%

    No Known Activations