© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198080
    Prev
    Next
    INDEX
    Explanations

    Hamish Harding or Pool Preserve

    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_4_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
    ↵
    0.93
    u
    0.77
    in
    0.73
    ção
    0.71
    s
    0.63
    an
    0.60
    នឹង
    0.59
    )
    0.58
    ️
    0.57
    spre
    0.56
    POSITIVE LOGITS
     ພວກເຮົາ
    0.79
    ο
    0.79
    ری
    0.78
    कृपया
    0.77
     cambia
    0.76
     direta
    0.74
     directa
    0.71
     organiza
    0.71
    ला
    0.70
     compris
    0.70
    Activations Density 0.003%

    No Known Activations