© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87048
    Prev
    Next
    INDEX
    Explanations

    square, Dam, Clustering, Remarque

    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
    ent
    1.02
    elle
    0.78
    AK
    0.74
    2
    0.74
    ando
    0.73
    ali
    0.69
    ert
    0.68
    ella
    0.68
    ette
    0.68
    ius
    0.67
    POSITIVE LOGITS
    ק
    0.84
    ی
    0.84
    
    0.78
    স
    0.75
    س
    0.73
    کي
    0.70
    рь
    0.69
    ח
    0.69
    ни
    0.68
    *'
    0.68
    Activations Density 0.019%

    No Known Activations