© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36415
    Prev
    Next
    INDEX
    Explanations

    . / – / ( / (~ / -

    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_31_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
    (),
    0.34
    ().
    0.34
    jén
    0.33
    (-)
    0.33
    brew
    0.32
    ","",
    0.32
    ()?;
    0.31
    ()},
    0.30
    (\
    0.30
     Labor
    0.30
    POSITIVE LOGITS
    ENSE
    0.35
    Hos
    0.34
    Principal
    0.33
    ense
    0.33
    جهات
    0.32
    Papa
    0.32
    soul
    0.31
     cią
    0.30
    灵魂
    0.30
    શો
    0.30
    Activations Density 0.113%

    No Known Activations