© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144887
    Prev
    Next
    INDEX
    Explanations

    comparably, comparison, comparators

    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_0_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
    ри
    1.49
    ן
    1.48
    in
    1.39
    ح
    1.38
    on
    1.37
    ोत्सव
    1.34
    는
    1.34
    ات
    1.30
    ных
    1.28
    ير
    1.28
    POSITIVE LOGITS
     by
    1.57
    M
    1.56
     at
    1.48
    G
    1.45
    5
    1.44
    D
    1.39
    K
    1.37
    ing
    1.31
     a
    1.30
     that
    1.30
    Activations Density 0.000%

    No Known Activations