© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14666
    Prev
    Next
    INDEX
    Explanations

    quoted speech starts

    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_15_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
    ین
    0.20
    ސް
    0.18
    roč
    0.17
    dengan
    0.17
    ovna
    0.17
    פ
    0.17
    มูล
    0.17
    ޕ
    0.17
    也会
    0.17
    ז
    0.17
    POSITIVE LOGITS
     Lé
    0.21
     puis
    0.19
     Loki
    0.19
     Soares
    0.18
     असामान्य
    0.18
     sprang
    0.17
     remarqué
    0.17
     Nú
    0.17
     Rouen
    0.17
     Sø
    0.17
    Activations Density 0.040%

    No Known Activations