© 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. 199984
    Prev
    Next
    INDEX
    Explanations

    ple

    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
    ombe
    0.49
     Ashton
    0.42
    órico
    0.42
     biot
    0.41
     Heather
    0.40
    biet
    0.39
    舸
    0.38
    био
    0.38
     upset
    0.38
    ビ
    0.38
    POSITIVE LOGITS
    एन
    0.39
    Ti
    0.38
    ဆို
    0.38
    Mana
    0.37
     millimeter
    0.36
    ন্‌
    0.36
    Prothorax
    0.35
     runways
    0.35
     Brion
    0.35
    localize
    0.34
    Activations Density 0.000%

    No Known Activations