© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110171
    Prev
    Next
    INDEX
    Explanations

    Tom's Diner, Hardware, Cabin, Robinson, Tomlinson

    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_2_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
    וד
    1.10
    お
    1.07
    お金
    1.02
    ある
    1.01
    น
    0.98
    すでに
    0.96
    お手
    0.95
    א
    0.95
    ಟರ್
    0.93
    おお
    0.92
    POSITIVE LOGITS
    were
    1.64
    :
    1.47
    i
    1.20
    in
    1.13
    won
    1.11
    washing
    1.01
     listar
    1.00
    =
    1.00
    ي
    1.00
    that
    0.98
    Activations Density 0.000%

    No Known Activations