© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54531
    Prev
    Next
    INDEX
    Explanations

    end of JSON/YAML/code blocks

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     搭
    0.42
    airan
    0.39
    KNOWN
    0.38
     Straits
    0.38
    نمية
    0.37
    Aircraft
    0.36
    Birthday
    0.36
    arda
    0.35
     ranch
    0.35
    圳
    0.35
    POSITIVE LOGITS
    čni
    0.37
     colonization
    0.35
    shiny
    0.35
    GetAsyncKeyState
    0.34
     поступ
    0.34
     хол
    0.34
    সেই
    0.33
    posY
    0.33
     pos
    0.32
     duration
    0.32
    Activations Density 0.103%

    No Known Activations