© 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. 86878
    Prev
    Next
    INDEX
    Explanations

    day names, itinerary, diet plan

    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
    ة
    0.74
    الية
    0.73
    EN
    0.72
     Ariana
    0.71
     ngày
    0.70
     Tahiti
    0.70
     doua
    0.69
     două
    0.68
     Nhiều
    0.68
    UZ
    0.68
    POSITIVE LOGITS
    s
    1.27
    t
    1.21
    ’
    0.93
    '
    0.84
    et
    0.83
    te
    0.78
    tor
    0.78
    v
    0.76
    ί
    0.74
    m
    0.73
    Activations Density 0.003%

    No Known Activations