© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61401
    Prev
    Next
    INDEX
    Explanations

    business industry

    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
    型
    0.68
    type
    0.58
     type
    0.57
    型の
    0.50
     型
    0.48
    式
    0.47
    型的
    0.46
    区
    0.46
     유형
    0.44
    typ
    0.43
    POSITIVE LOGITS
    业
    0.47
    業
    0.43
    업
    0.39
    рёх
    0.37
     INDUSTRY
    0.37
     suit
    0.35
     महे
    0.35
     negocios
    0.34
     Monterrey
    0.34
    चणी
    0.34
    Activations Density 0.007%

    No Known Activations