© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153025
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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_23_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
     chromedp
    0.42
    Inputs
    0.41
     చేస్త
    0.40
     输入
    0.39
     สํา
    0.39
    谢谢
    0.39
     ಮುಖ್ಯ
    0.39
    唬
    0.39
    쎄
    0.39
    预约
    0.38
    POSITIVE LOGITS
    auro
    0.38
     ISO
    0.37
     U
    0.36
    uma
    0.36
    rcl
    0.35
     Football
    0.35
     o
    0.35
     de
    0.35
     Quickly
    0.35
     A
    0.34
    Activations Density 0.001%

    No Known Activations