© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11192
    Prev
    Next
    INDEX
    Explanations

    people and places

    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_13_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
    ling
    0.55
    Racing
    0.50
    rugated
    0.49
    ering
    0.49
     ‘
    0.48
    registr
    0.48
    outs
    0.48
    c
    0.48
    cussion
    0.48
    Weitere
    0.48
    POSITIVE LOGITS
     AFTER
    0.60
    从
    0.57
     bisogno
    0.54
     CREE
    0.53
     мысли
    0.48
     моги
    0.48
     家
    0.48
    คิด
    0.48
     بیچ
    0.48
    செல்
    0.48
    Activations Density 0.002%

    No Known Activations