© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204014
    Prev
    Next
    INDEX
    Explanations

    grö/Ge, Gö/Gö, öß, Gröbner

    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_6_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
     in
    1.37
    ہ
    1.19
    ک
    1.04
    ח
    0.93
    يل
    0.90
     to
    0.85
    q
    0.85
    ק
    0.85
    ム
    0.85
    پ
    0.84
    POSITIVE LOGITS
    1
    1.16
    ed
    1.02
    ER
    1.01
    1.01
    nya
    0.97
    as
    0.95
     Toma
    0.93
    iad
    0.89
    at
    0.88
    roje
    0.86
    Activations Density 0.000%

    No Known Activations