© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77742
    Prev
    Next
    INDEX
    Explanations

    contrast or exception

    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_29_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
    属于
    0.38
    ومة
    0.37
    ֩
    0.35
     przypad
    0.34
     Developmental
    0.34
    inous
    0.34
    genuine
    0.34
     artificial
    0.33
     nos
    0.33
     Artificial
    0.33
    POSITIVE LOGITS
     {}>,
    0.38
     jsx
    0.37
    Not
    0.37
     অপেক্ষায়
    0.37
     محاضره
    0.37
     vagu
    0.37
     علاقه
    0.36
     bukan
    0.36
    糾
    0.36
     arrêter
    0.36
    Activations Density 0.006%

    No Known Activations