© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18264
    Prev
    Next
    INDEX
    Explanations

    fontFamily: sans-serif

    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
    Electricity
    0.36
    –
    0.35
     Electricity
    0.32
     dith
    0.32
    (
    0.32
     Light
    0.32
    -
    0.32
     Crist
    0.31
     Crom
    0.30
    -_
    0.30
    POSITIVE LOGITS
     جو
    0.38
    űt
    0.36
     jó
    0.34
    ತಾ
    0.34
     Boko
    0.34
    scholar
    0.33
    𝖙
    0.33
     ಜೋ
    0.33
    getRow
    0.33
     लग
    0.32
    Activations Density 0.004%

    No Known Activations