© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9095
    Prev
    Next
    INDEX
    Explanations

    sassy

    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_13_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
    ای
    0.58
    recipes
    0.53
    goods
    0.51
    もら
    0.51
    day
    0.51
    सीबी
    0.51
    인
    0.51
    온
    0.51
    Stranger
    0.50
    patient
    0.49
    POSITIVE LOGITS
     spirit
    0.66
     rebellion
    0.60
     theft
    0.54
     ס
    0.54
     s
    0.52
    0.51
    </h3>
    0.50
     movement
    0.50
     scout
    0.50
     phrase
    0.50
    Activations Density 0.003%

    No Known Activations