© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44314
    Prev
    Next
    INDEX
    Explanations

    in-depth investigation or analysis

    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_3_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
    ,
    0.89
    d
    0.87
    r
    0.75
    고
    0.68
    M
    0.68
    র
    0.67
    .
    0.66
     is
    0.65
    ।
    0.65
    ز
    0.63
    POSITIVE LOGITS
    見
    0.69
    약
    0.64
    ни
    0.61
    含有
    0.61
     développ
    0.56
    ದ್ದರಿಂದ
    0.56
    getBy
    0.55
    spacePad
    0.54
    事は
    0.53
     હતી
    0.52
    Activations Density 0.001%

    No Known Activations