© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42157
    Prev
    Next
    INDEX
    Explanations

    CLI argument parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     Beziehungen
    0.42
    鍰
    0.42
     prisoner
    0.41
     coupons
    0.40
     divorced
    0.40
     institu
    0.39
     består
    0.39
     mengetahui
    0.39
     imprisoned
    0.38
    Ỉ
    0.38
    POSITIVE LOGITS
    chard
    0.45
    ਨਾ
    0.40
    刈
    0.39
     ולה
    0.38
    inductive
    0.38
    fontenc
    0.37
     sequentially
    0.37
     നാ
    0.37
     initially
    0.36
    пада
    0.36
    Activations Density 0.000%

    No Known Activations