© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42972
    Prev
    Next
    INDEX
    Explanations

    responding to opposition or comments

    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_13_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
    b
    0.27
    ب
    0.26
    let
    0.26
    ’
    0.26
     Therapeutic
    0.25
    h
    0.25
    ↵↵
    0.25
    v
    0.24
    的
    0.24
     information
    0.24
    POSITIVE LOGITS
     testifies
    0.29
     причины
    0.29
     unsh
    0.27
    нді
    0.27
    cznie
    0.27
     shampoos
    0.27
     نفسي
    0.26
     vesicles
    0.25
     المكتب
    0.25
     petitions
    0.25
    Activations Density 0.021%

    No Known Activations