© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92729
    Prev
    Next
    INDEX
    Explanations

    future intent

    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_60_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
     look
    0.50
    look
    0.46
     Look
    0.46
    Look
    0.45
     ucfirst
    0.38
    ஸ
    0.37
     try
    0.36
    擴
    0.36
    ஸில்
    0.36
    證據
    0.36
    POSITIVE LOGITS
     Subjects
    0.77
    Subjects
    0.76
     Provide
    0.70
     subjects
    0.69
     Subject
    0.67
    Subject
    0.63
     leveraging
    0.63
    Provide
    0.63
    subjects
    0.62
     provide
    0.61
    Activations Density 0.002%

    No Known Activations