© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131501
    Prev
    Next
    INDEX
    Explanations

    grant proposal or application

    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_1_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
    s
    1.36
    あ
    1.10
     energ
    0.99
     reorgan
    0.93
    上
    0.93
    不少
    0.93
    使用
    0.90
    出
    0.90
    我
    0.89
    in
    0.88
    POSITIVE LOGITS
    ри
    1.38
    ai
    0.98
    ore
    0.91
    (),
    0.91
    ie
    0.90
    рида
    0.87
    ן
    0.86
    <0xA0>
    0.86
    ва
    0.85
    ö
    0.85
    Activations Density 0.000%

    No Known Activations