© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141379
    Prev
    Next
    INDEX
    Explanations

    super().__init__ or __init__

    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_12_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
    il
    0.86
     l
    0.83
     n
    0.82
     by
    0.78
     e
    0.77
    im
    0.77
    ino
    0.77
    er
    0.76
     It
    0.75
     re
    0.74
    POSITIVE LOGITS
    dengan
    0.83
    ﺪ
    0.75
    მასრულ
    0.75
    PARATION
    0.74
    დომ
    0.71
    тай
    0.71
    FDMA
    0.69
     Vestone
    0.68
    𝗗
    0.68
    𝓭
    0.68
    Activations Density 0.017%

    No Known Activations