© 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. 253643
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
     EXEC
    0.39
    ified
    0.38
     langue
    0.38
     língua
    0.37
    يبه
    0.37
    َي
    0.36
    ATUS
    0.36
    trib
    0.36
    க்கி
    0.35
    ifications
    0.34
    POSITIVE LOGITS
     Kuy
    0.43
    ಒ
    0.40
     Cub
    0.40
    Ku
    0.40
    cstdlib
    0.38
     Stry
    0.38
     Cu
    0.37
    ্ষিক
    0.37
     Ku
    0.37
     Dayan
    0.37
    Activations Density 0.000%

    No Known Activations