© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200216
    Prev
    Next
    INDEX
    Explanations

    python multiprocessing

    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_12_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
    </h2>
    0.48
     {
    0.45
    shoes
    0.43
    ang
    0.42
     pico
    0.41
     com
    0.41
    y
    0.41
     in
    0.40
    ಗೊಳ್ಳ
    0.40
    fus
    0.40
    POSITIVE LOGITS
    柤
    0.49
    𓇼
    0.41
     trấn
    0.40
    тят
    0.40
    邡
    0.40
     Extern
    0.39
    ставля
    0.39
    неш
    0.39
     miệng
    0.39
    avkh
    0.39
    Activations Density 0.002%

    No Known Activations