© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115846
    Prev
    Next
    INDEX
    Explanations

    sugar in recipes

    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_27_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
    ി
    0.42
    毎日
    0.37
     prec
    0.36
     ማስ
    0.36
    CAP
    0.35
    Recommend
    0.35
     href
    0.35
    Secrets
    0.34
     situational
    0.34
    HttpContext
    0.34
    POSITIVE LOGITS
    ulación
    0.41
    edio
    0.39
     eme
    0.37
    峒
    0.37
     intim
    0.36
    embros
    0.36
    vollen
    0.35
    resTmp
    0.35
    菁
    0.35
    renaline
    0.35
    Activations Density 0.004%

    No Known Activations