© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50317
    Prev
    Next
    INDEX
    Explanations

    up to date

    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_10_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
    fordern
    0.62
    ү
    0.62
    мі
    0.59
     whereupon
    0.59
    器
    0.58
     derr
    0.56
     piani
    0.56
    язы
    0.56
    佽
    0.56
    вість
    0.55
    POSITIVE LOGITS
    h
    0.68
     पॉइंट
    0.59
    t
    0.59
    σε
    0.56
     तुमच्या
    0.56
    enregist
    0.55
     LAS
    0.55
     vegetales
    0.55
     verzek
    0.55
    f
    0.54
    Activations Density 0.018%

    No Known Activations