© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80029
    Prev
    Next
    INDEX
    Explanations

    panderer, Icelander, Neanderthal

    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_0_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
    يد
    1.43
     carénés
    1.39
     Antennes
    1.38
    ಬ್ಬಿಣ
    1.36
    та
    1.35
    ués
    1.34
    ﻪ
    1.30
    の高い
    1.29
     óptica
    1.28
    ا
    1.27
    POSITIVE LOGITS
    ade
    1.86
    D
    1.82
    T
    1.80
    M
    1.77
     an
    1.71
    G
    1.61
    ?
    1.58
     a
    1.55
     on
    1.50
    _
    1.45
    Activations Density 0.001%

    No Known Activations