© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85816
    Prev
    Next
    INDEX
    Explanations

    coffee break

    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_3_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
    a
    0.98
    ت
    0.69
    o
    0.66
    setVisibility
    0.65
    ه
    0.64
    و
    0.64
    GL
    0.63
    qt
    0.62
    il
    0.62
    没有什么
    0.62
    POSITIVE LOGITS
     inhab
    0.67
     também
    0.63
     το
    0.63
     וש
    0.62
     وي
    0.61
     électriques
    0.61
    ི་
    0.60
    éd
    0.60
     ל
    0.59
     esta
    0.59
    Activations Density 0.010%

    No Known Activations