© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36535
    Prev
    Next
    INDEX
    Explanations

    legendary

    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
    t
    0.65
     For
    0.61
     foray
    0.61
    b
    0.61
     convirtió
    0.59
     jun
    0.58
     flurry
    0.58
     photometric
    0.58
     قريب
    0.58
    否
    0.57
    POSITIVE LOGITS
    ন
    0.90
     are
    0.75
     conditioners
    0.74
     alignments
    0.73
    ра
    0.73
    रा
    0.71
    را
    0.70
    ug
    0.69
    ibilities
    0.68
    लया
    0.68
    Activations Density 0.005%

    No Known Activations