© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35317
    Prev
    Next
    INDEX
    Explanations

    services and management

    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_31_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
     Meghna
    0.39
     Pottery
    0.39
     acetone
    0.38
     Fittings
    0.38
     angin
    0.38
     ko
    0.37
    raphe
    0.36
     ত
    0.36
     Koo
    0.35
     adjoining
    0.35
    POSITIVE LOGITS
     contracted
    0.43
    管理
    0.42
    ับสนุน
    0.41
    的管理
    0.41
     break
    0.40
     управления
    0.40
    管理的
    0.40
    management
    0.39
     управління
    0.39
    ത്തില്‍
    0.39
    Activations Density 0.037%

    No Known Activations