© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39875
    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_57_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
    闶
    0.39
     amort
    0.38
    lerim
    0.38
     Technologie
    0.38
    setPassword
    0.38
    arları
    0.37
    曲线
    0.36
    lini
    0.36
     convexity
    0.36
     பக்கம்
    0.35
    POSITIVE LOGITS
    셉
    0.39
    Accom
    0.38
    റ്റ
    0.38
    ွား
    0.38
    Acet
    0.37
     Aw
    0.37
    क्त
    0.36
    تب
    0.36
    Affect
    0.36
    億
    0.36
    Activations Density 0.000%

    No Known Activations