© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16652
    Prev
    Next
    INDEX
    Explanations

    shapes and geometric arrangements

    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
     정사각형
    0.08
     segmento
    0.08
     FullHD
    0.08
    toll
    0.08
     Pleasure
    0.08
     BBQ
    0.07
     TL
    0.07
    堌
    0.07
     TV
    0.07
     Corolla
    0.07
    POSITIVE LOGITS
     bonuses
    0.09
     bombings
    0.08
     jabatan
    0.08
     ruining
    0.08
     abstinence
    0.08
     councils
    0.08
     municipalities
    0.08
     extracts
    0.08
     unix
    0.08
     embargo
    0.08
    Activations Density 0.099%

    No Known Activations