© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198635
    Prev
    Next
    INDEX
    Explanations

    logging framework

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     move
    0.56
     Move
    0.56
    move
    0.48
    鯰
    0.46
     moves
    0.45
    Move
    0.44
     MOVE
    0.44
     дви
    0.41
     Moved
    0.40
    moves
    0.40
    POSITIVE LOGITS
    erian
    0.48
    Kyle
    0.40
    리카
    0.40
    경
    0.40
    Mater
    0.39
     Kyle
    0.39
     Israeli
    0.38
    Israeli
    0.38
     Wasserstein
    0.38
     Mile
    0.37
    Activations Density 0.000%

    No Known Activations