© 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. 23462
    Prev
    Next
    INDEX
    Explanations

    Web

    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
    storm
    0.36
    vivo
    0.36
     कर्म
    0.34
    burning
    0.34
    年も
    0.33
     togg
    0.33
     व्ह
    0.33
    랭
    0.33
    BB
    0.32
    dis
    0.32
    POSITIVE LOGITS
     effective
    0.55
     эффектив
    0.53
    effective
    0.52
    page
    0.52
     Effective
    0.51
    有效的
    0.49
    Effective
    0.49
     efektif
    0.49
    ไซต์
    0.47
    sites
    0.47
    Activations Density 0.007%

    No Known Activations