© 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. 24162
    Prev
    Next
    INDEX
    Explanations

    foreign 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
     ദി
    0.46
    the
    0.44
     the
    0.44
    THE
    0.42
     THE
    0.39
    ザ
    0.38
     îl
    0.37
    thel
    0.37
    ethe
    0.36
    いの
    0.36
    POSITIVE LOGITS
     główn
    0.45
     ostat
    0.41
     ไฟล์
    0.40
     самым
    0.37
    sberg
    0.35
    灑
    0.34
     जिन
    0.33
     naj
    0.32
     afgelopen
    0.32
     entwick
    0.32
    Activations Density 0.000%

    No Known Activations