© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198272
    Prev
    Next
    INDEX
    Explanations

    promotion

    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
    adores
    0.29
    ası
    0.28
    ائز
    0.27
    採用
    0.26
    ormal
    0.26
    0
    0.25
    ildi
    0.25
    וע
    0.25
    ak
    0.24
    ulkar
    0.24
    POSITIVE LOGITS
     splatter
    0.31
     DataType
    0.29
     subjunctive
    0.29
    culoskeletal
    0.29
     მათი
    0.29
     gingham
    0.29
     Vem
    0.28
    苙
    0.28
     Neville
    0.28
     Zeke
    0.28
    Activations Density 0.003%

    No Known Activations