© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131189
    Prev
    Next
    INDEX
    Explanations

    biscuits

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Trot
    0.54
     paw
    0.51
     Corn
    0.50
    Paw
    0.48
     Paw
    0.47
     trot
    0.47
     corn
    0.44
    촘
    0.44
    Corn
    0.42
     Acre
    0.42
    POSITIVE LOGITS
    bis
    0.60
    Bis
    0.59
     biscuits
    0.55
     kol
    0.54
     bis
    0.53
     Bis
    0.50
    Kol
    0.49
    ビス
    0.47
     obliqu
    0.46
     biscuit
    0.45
    Activations Density 0.039%

    No Known Activations