© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13682
    Prev
    Next
    INDEX
    Explanations

    GPU power and components

    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_13_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
    친
    0.59
    ва
    0.58
    کان
    0.57
    의
    0.57
    Hepinize
    0.55
    ⃝
    0.55
     linearization
    0.54
    ൮
    0.54
    밖
    0.52
    적
    0.52
    POSITIVE LOGITS
    ュ
    0.56
     Kenya
    0.54
    クス
    0.52
    ul
    0.52
     Treasures
    0.51
     MPs
    0.50
     Curly
    0.50
     Harrier
    0.49
     Getty
    0.49
     Pearson
    0.48
    Activations Density 0.055%

    No Known Activations