© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175334
    Prev
    Next
    INDEX
    Explanations

    compliments for appearance and positivity

    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_20_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
    OrderFlight
    0.27
    ђа
    0.26
    >]</
    0.25
    getWriter
    0.25
    γε
    0.25
     معاش
    0.25
    렐
    0.25
    сова
    0.25
    鲛
    0.24
    临时
    0.24
    POSITIVE LOGITS
     retention
    0.30
    ification
    0.29
     EG
    0.29
     tipo
    0.28
    ی
    0.28
     conserved
    0.27
     sogar
    0.27
     PCs
    0.27
     silky
    0.27
     segreg
    0.27
    Activations Density 0.000%

    No Known Activations