© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62222
    Prev
    Next
    INDEX
    Explanations

    unzipping zip

    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_2_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
    1.24
    in
    1.19
    。</
    1.19
    have
    1.13
     It
    1.12
     have
    1.11
    I
    1.07
    听
    1.05
    ו
    1.05
    com
    1.01
    POSITIVE LOGITS
    ла
    1.52
    ದ
    1.45
    もら
    1.37
    га
    1.28
    ດີ
    1.27
    त
    1.25
    дите
    1.20
    ле
    1.19
    σε
    1.19
    も
    1.18
    Activations Density 0.001%

    No Known Activations