© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51938
    Prev
    Next
    INDEX
    Explanations

    insurance

    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_55_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
     covered
    0.39
    ංශ
    0.39
    arton
    0.39
     tercero
    0.39
     cover
    0.38
    cover
    0.38
    covered
    0.36
     ಘ
    0.36
    noh
    0.36
    ynamics
    0.36
    POSITIVE LOGITS
    審査
    0.45
     agencies
    0.44
     Agencies
    0.41
    Accommodation
    0.40
     विनियम
    0.40
    信息化
    0.39
     Counseling
    0.38
    श्विक
    0.38
    违法
    0.38
     verification
    0.37
    Activations Density 0.003%

    No Known Activations