© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201386
    Prev
    Next
    INDEX
    Explanations

    act, action, Adams, Italian

    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_37_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
    🍨
    0.42
     बुला
    0.42
     тебе
    0.42
     segera
    0.40
    estern
    0.40
    這些
    0.39
    提及
    0.39
     need
    0.39
    鈴木
    0.39
     დ
    0.39
    POSITIVE LOGITS
     Maugin
    0.48
     raster
    0.43
    ಜ್ಞ
    0.40
    ey
    0.39
    CAST
    0.39
     CAST
    0.39
    값이
    0.38
    cartes
    0.38
     Są
    0.36
    分辨率
    0.36
    Activations Density 0.000%

    No Known Activations