© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133857
    Prev
    Next
    INDEX
    Explanations

    surpassing

    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
     页
    0.40
    Zak
    0.38
    polyfills
    0.38
    殿
    0.38
    pple
    0.37
    णं
    0.37
    anooga
    0.36
    ῃ
    0.36
    Derivative
    0.35
    φέ
    0.35
    POSITIVE LOGITS
    per
    0.89
    пер
    0.83
    เปอร์
    0.83
    perc
    0.75
    PER
    0.74
     perc
    0.73
    퍼
    0.70
     Perc
    0.67
    перы
    0.67
    パー
    0.66
    Activations Density 0.001%

    No Known Activations