© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31896
    Prev
    Next
    INDEX
    Explanations

    StyleSheet.create

    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_40_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
    pyrrol
    0.40
     nových
    0.38
    plash
    0.37
     धूम
    0.36
    |$.
    0.36
    PDM
    0.36
     új
    0.35
    Material
    0.35
     merchandise
    0.35
    pyrid
    0.35
    POSITIVE LOGITS
     attach
    0.41
    üt
    0.40
     attaching
    0.39
     tattha
    0.39
     붙
    0.39
     natthi
    0.38
     accompagn
    0.38
    붙
    0.37
    attach
    0.36
     atte
    0.36
    Activations Density 0.000%

    No Known Activations