© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78630
    Prev
    Next
    INDEX
    Explanations

    cookies and baking

    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
     dialogues
    0.40
     dialogue
    0.39
    農
    0.38
     dia
    0.37
    dialog
    0.36
     농
    0.36
    閲
    0.36
     農
    0.36
    inium
    0.35
    农
    0.35
    POSITIVE LOGITS
    🍪
    0.47
     cookies
    0.46
     Cookies
    0.44
    Cookie
    0.42
    cookies
    0.40
     risultati
    0.40
     cookie
    0.39
    Cookies
    0.39
     પહો
    0.37
    licken
    0.36
    Activations Density 0.033%

    No Known Activations