© 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. 37433
    Prev
    Next
    INDEX
    Explanations

    News, Mail, article, server

    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
    าศ
    0.71
    ంక
    0.68
     aplicativo
    0.64
    춰
    0.61
     Operations
    0.60
     hodin
    0.59
     Хо
    0.58
     Ways
    0.58
     Helpers
    0.58
     Procedure
    0.58
    POSITIVE LOGITS
    ला
    1.09
    ные
    0.94
    is
    0.91
    на
    0.87
    る
    0.80
    ли
    0.80
    ре
    0.79
    sun
    0.79
    on
    0.78
    ub
    0.78
    Activations Density 0.000%

    No Known Activations