© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169399
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     /
    0.34
     sed
    0.33
    ｜
    0.32
    ;}
    0.31
    》，
    0.29
    利润
    0.29
     পি
    0.29
    :`
    0.29
     mę
    0.28
     技術
    0.28
    POSITIVE LOGITS
    smaller
    0.31
    भी
    0.30
    could
    0.30
    tikz
    0.30
    s
    0.30
    anomaly
    0.30
    ສາມາດ
    0.30
    munder
    0.29
    თავ
    0.29
    ی
    0.29
    Activations Density 0.003%

    No Known Activations