© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45285
    Prev
    Next
    INDEX
    Explanations

    tape and lists

    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
    ج
    0.95
    ش
    0.83
    ’
    0.79
     Transporte
    0.79
    ي
    0.77
    ни
    0.70
     profiter
    0.70
    দু
    0.68
    wirkungen
    0.68
    ிக்க
    0.67
    POSITIVE LOGITS
    1.30
     are
    1.02
    S
    0.87
     (
    0.84
     a
    0.76
    isotropic
    0.75
     infrared
    0.74
     kēia
    0.73
     appear
    0.71
     chaotic
    0.71
    Activations Density 0.006%

    No Known Activations