© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234233
    Prev
    Next
    INDEX
    Explanations

    how many pieces or balls

    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_32_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
     Nói
    0.42
     bảo
    0.41
     protecting
    0.40
    គោ
    0.40
     alternator
    0.39
     защита
    0.39
     ഏക
    0.39
    捍
    0.39
    ើរ
    0.38
     protection
    0.38
    POSITIVE LOGITS
     수는
    0.41
    传染
    0.36
    悠
    0.36
    ギュラー
    0.35
     Verbre
    0.35
    юро
    0.34
     ㄱ
    0.34
    лле
    0.34
    ovsk
    0.33
    쥘
    0.33
    Activations Density 0.007%

    No Known Activations