© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195881
    Prev
    Next
    INDEX
    Explanations

    Slavic endings

    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_50_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
    atrième
    0.41
     লন্ডন
    0.40
    付
    0.39
    zf
    0.39
    즈
    0.39
    Brush
    0.38
    ^{*}+
    0.38
    őz
    0.38
    ili
    0.37
    engin
    0.37
    POSITIVE LOGITS
    kov
    0.41
     uda
    0.41
    ков
    0.40
    यों
    0.40
    oinette
    0.38
    の高
    0.38
    кові
    0.38
    pok
    0.38
    isometric
    0.38
    র্ষণ
    0.38
    Activations Density 0.000%

    No Known Activations