© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147044
    Prev
    Next
    INDEX
    Explanations

    feel

    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_59_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
    貢
    0.38
    蕨
    0.36
     correlated
    0.35
    想着
    0.35
     '@
    0.33
     accessed
    0.33
     Honorary
    0.33
     presenta
    0.33
     '\''
    0.33
    冒
    0.33
    POSITIVE LOGITS
    seen
    0.55
     Seen
    0.55
    Seen
    0.54
    Psych
    0.52
     vistos
    0.52
     seen
    0.52
    psych
    0.49
     دیده
    0.48
     види
    0.47
     Psych
    0.46
    Activations Density 0.002%

    No Known Activations