© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58965
    Prev
    Next
    INDEX
    Explanations

    say "0" or "z" 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_59_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
     امام
    0.37
    芡
    0.34
    恴
    0.34
     imam
    0.33
    WeakTable
    0.33
    まえ
    0.33
     حلق
    0.33
    ოკ
    0.33
    内
    0.33
    ไม
    0.32
    POSITIVE LOGITS
     zero
    1.56
    zero
    1.52
    Zero
    1.43
     Zero
    1.39
     ZERO
    1.31
    零
    1.30
    ZERO
    1.27
    ゼロ
    1.19
     become
    1.16
    become
    1.14
    Activations Density 0.006%

    No Known Activations