© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54545
    Prev
    Next
    INDEX
    Explanations

    loan/letter/glove/findings

    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_30_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
     정신
    0.37
    デザイン
    0.36
    gegen
    0.36
     Design
    0.35
    SECOND
    0.35
     Doming
    0.35
     DIG
    0.35
     औ
    0.34
     &
    0.34
     Nico
    0.34
    POSITIVE LOGITS
    Penalty
    0.40
    tbx
    0.40
     biến
    0.39
     webbrowser
    0.39
    某一
    0.39
    混乱
    0.38
     boz
    0.37
    aic
    0.36
     confusión
    0.36
    浏览器
    0.36
    Activations Density 0.000%

    No Known Activations