© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110585
    Prev
    Next
    INDEX
    Explanations

    bins

    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_2_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
    1.02
     форма
    0.82
    ;
    0.79
     يع
    0.72
     ово
    0.70
     όχι
    0.69
     onge
    0.68
     أبو
    0.68
     поги
    0.66
     is
    0.66
    POSITIVE LOGITS
    л
    1.03
    ल
    1.00
    it
    0.93
    ि
    0.93
    ле
    0.91
    ات
    0.90
    ל
    0.88
    on
    0.87
    as
    0.84
    দের
    0.81
    Activations Density 0.003%

    No Known Activations