© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139503
    Prev
    Next
    INDEX
    Explanations

    European Space Agency / Organization

    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_12_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
    sa
    0.49
    leri
    0.49
    de
    0.46
    żliw
    0.46
    >"
    0.45
    ler
    0.45
     calmed
    0.44
    señ
    0.44
     hydrated
    0.43
    Critics
    0.43
    POSITIVE LOGITS
    
    0.46
     Mash
    0.43
     Cub
    0.41
    Liqu
    0.41
     Rape
    0.41
     OpenGL
    0.40
    ков
    0.40
    ورة
    0.40
     prilikom
    0.40
     Karate
    0.40
    Activations Density 0.000%

    No Known Activations