© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92443
    Prev
    Next
    INDEX
    Explanations

    endearing

    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_11_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
    druck
    0.73
     الزد
    0.69
    ❙
    0.69
    ndvi
    0.63
    ।*
    0.62
    ➋
    0.61
    пия
    0.61
    ফুজ
    0.61
    setosa
    0.61
    ギリス
    0.60
    POSITIVE LOGITS
     startling
    0.59
    g
    0.58
    P
    0.58
     compteur
    0.54
    ﻋ
    0.54
     πάνω
    0.54
    म्र
    0.53
     ή
    0.52
     whereabouts
    0.52
    p
    0.52
    Activations Density 0.001%

    No Known Activations