© 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. 86945
    Prev
    Next
    INDEX
    Explanations

    River, wool, ities

    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
    ۔
    0.78
     figlio
    0.74
    。
    0.74
    টা
    0.73
    ");
    0.69
    ’
    0.68
    ך
    0.67
    ።
    0.67
    จะ
    0.65
     poziom
    0.65
    POSITIVE LOGITS
    lig
    0.88
    lige
    0.81
    elje
    0.81
    g
    0.81
    gates
    0.80
    u
    0.78
    tedir
    0.78
    mars
    0.77
    lars
    0.77
    gents
    0.77
    Activations Density 0.000%

    No Known Activations