© 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. 34991
    Prev
    Next
    INDEX
    Explanations

    Founding Fathers

    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
    1.20
    g
    0.92
    o
    0.86
    at
    0.82
    nå
    0.80
    y
    0.80
    p
    0.79
    melon
    0.75
    går
    0.75
    v
    0.73
    POSITIVE LOGITS
    に
    0.67
    స్‌
    0.62
    נ
    0.62
     என்று
    0.61
    的热
    0.60
     operazioni
    0.60
     odpowiedzi
    0.60
     izinsuku
    0.58
     demonstrate
    0.57
     podría
    0.57
    Activations Density 0.000%

    No Known Activations