© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195791
    Prev
    Next
    INDEX
    Explanations

    Alice

    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_15_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
     that
    0.32
    ंना
    0.31
     и
    0.28
    iseen
    0.28
    aney
    0.28
    ↵↵
    0.28
     Ural
    0.27
     salad
    0.27
    ंनी
    0.27
    和
    0.26
    POSITIVE LOGITS
    Check
    0.30
    HOME
    0.30
    Petit
    0.30
    Sleep
    0.30
    ParentElement
    0.29
    MONTH
    0.29
    Пре
    0.29
    Denote
    0.29
    অব
    0.29
    Cells
    0.28
    Activations Density 0.002%

    No Known Activations