© 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. 35118
    Prev
    Next
    INDEX
    Explanations

    parts of the world

    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
     գ
    0.68
     ασ
    0.67
     האי
    0.63
     excellente
    0.62
     Mayıs
    0.62
     ανα
    0.61
     ανθ
    0.59
     ηλεκ
    0.58
    parts
    0.58
     ανε
    0.58
    POSITIVE LOGITS
    را
    0.92
    ри
    0.88
    ២
    0.84
    не
    0.82
    ні
    0.81
    ра
    0.81
    ار
    0.80
    de
    0.80
    ко
    0.73
    ست
    0.72
    Activations Density 0.011%

    No Known Activations