© 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. 253533
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
    ীণ
    0.40
    ок
    0.38
    ранд
    0.38
    PAL
    0.37
    (../
    0.36
    |[
    0.36
    :["
    0.35
    ит
    0.35
    Xc
    0.35
    ණ
    0.35
    POSITIVE LOGITS
     nying
    0.45
    す
    0.41
     mistake
    0.41
    aque
    0.39
     sme
    0.39
     sna
    0.38
     wk
    0.38
     suo
    0.38
     sus
    0.37
     nele
    0.37
    Activations Density 0.001%

    No Known Activations