© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99382
    Prev
    Next
    INDEX
    Explanations

    Taco

    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_16_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
     美術
    0.53
    ربية
    0.50
     الصحة
    0.49
     nächsten
    0.47
     הספר
    0.47
     மண்ண
    0.46
     beaches
    0.45
     એ
    0.44
    ။
    0.44
     工具
    0.44
    POSITIVE LOGITS
    u
    0.45
    筷
    0.44
     disadvant
    0.43
     advantage
    0.42
     vjer
    0.42
    Z
    0.42
     पुरे
    0.41
     advantages
    0.41
    逆に
    0.41
    bile
    0.41
    Activations Density 0.000%

    No Known Activations