© 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. 90026
    Prev
    Next
    INDEX
    Explanations

    cover art

    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
     couverts
    0.89
    ي
    0.79
    teams
    0.74
    w
    0.74
     покрытия
    0.72
     covered
    0.71
    tig
    0.71
    covered
    0.71
    ر
    0.71
     smothered
    0.70
    POSITIVE LOGITS
    لی
    0.64
    า
    0.63
     federation
    0.60
    eningrad
    0.60
    াইল
    0.59
    ;
    0.59
     wardrobe
    0.58
    ell
    0.57
    開催
    0.57
     superpower
    0.57
    Activations Density 0.003%

    No Known Activations