© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252448
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_56_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
    ｪ
    0.38
    idane
    0.35
    cap
    0.35
    unud
    0.35
     ৪র্থ
    0.34
    ровкой
    0.34
    琿
    0.33
    uhi
    0.33
    antz
    0.33
     ২টি
    0.33
    POSITIVE LOGITS
     Two
    1.28
     Three
    1.17
    Two
    1.16
     Eight
    1.13
     二
    1.13
     Five
    1.11
    二
    1.11
     Four
    1.09
    Three
    1.09
     TWO
    1.07
    Activations Density 0.002%

    No Known Activations