© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57958
    Prev
    Next
    INDEX
    Explanations

    stepping down from

    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_11_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
    д
    0.64
    ivals
    0.56
    ب
    0.52
     contenders
    0.51
    atoms
    0.50
    স
    0.50
    acul
    0.50
    DEFIN
    0.50
     ومل
    0.50
    ス
    0.50
    POSITIVE LOGITS
    toare
    0.60
     hang
    0.54
     năm
    0.53
    尽可能
    0.53
    下来
    0.52
     decompose
    0.50
     amateur
    0.50
     bevel
    0.50
     netting
    0.49
    sächlich
    0.49
    Activations Density 0.001%

    No Known Activations