© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26427
    Prev
    Next
    INDEX
    Explanations

    sherbet and sorbet

    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_10_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
    r
    0.82
    ต
    0.77
    on
    0.75
    不说
    0.71
     not
    0.67
    の
    0.67
    C
    0.66
    /
    0.65
    t
    0.65
    osphere
    0.63
    POSITIVE LOGITS
    ే
    0.66
     যান
    0.64
    েশন
    0.63
    ᱗
    0.62
     auxquelles
    0.62
    σης
    0.61
    κης
    0.60
    ']>;
    0.60
     Zentr
    0.58
    ༨
    0.58
    Activations Density 0.002%

    No Known Activations