© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45003
    Prev
    Next
    INDEX
    Explanations

    constructor calls (`base(...)`, `super(...)`)

    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_22_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
    들이
    0.43
    장이
    0.41
     assured
    0.40
    visual
    0.40
     daffodils
    0.40
    구
    0.40
    кре
    0.40
     creatinine
    0.39
    меч
    0.39
    구가
    0.39
    POSITIVE LOGITS
    américa
    0.41
     DAYS
    0.40
    ואה
    0.40
    America
    0.39
     AMS
    0.39
     America
    0.39
     വരെ
    0.39
     Runtime
    0.38
    aime
    0.38
    禍
    0.38
    Activations Density 0.000%

    No Known Activations