© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 148746
    Prev
    Next
    INDEX
    Explanations

    effective, safe

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     гря
    0.49
    ренности
    0.43
    тости
    0.43
    женности
    0.42
    ственности
    0.38
    ністю
    0.37
    емости
    0.37
    讠
    0.36
    ostí
    0.35
     Parse
    0.35
    POSITIVE LOGITS
     безопас
    0.65
     эффектив
    0.63
     отме
    0.62
     тре
    0.46
     реально
    0.45
    ствен
    0.44
     ответствен
    0.43
     એવી
    0.43
     americ
    0.42
     tre
    0.42
    Activations Density 0.001%

    No Known Activations