© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89041
    Prev
    Next
    INDEX
    Explanations

    informal address "ya"

    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
    다
    0.61
    <0x0D>
    0.60
     orice
    0.58
    ール
    0.54
    o
    0.54
    ﻊ
    0.54
    ra
    0.53
    ত
    0.53
     که
    0.52
    ো
    0.52
    POSITIVE LOGITS
     evacu
    0.51
     lived
    0.50
     ولكن
    0.49
     koh
    0.49
     wund
    0.49
     frogs
    0.49
     defin
    0.48
    工作
    0.48
     tortured
    0.48
     dafür
    0.47
    Activations Density 0.002%

    No Known Activations