© 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. 61379
    Prev
    Next
    INDEX
    Explanations

    third person male

    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
    彼
    0.43
    تها
    0.41
    heter
    0.40
    hell
    0.40
     nią
    0.40
     său
    0.39
     Seine
    0.39
    helic
    0.38
    hess
    0.38
    हत
    0.37
    POSITIVE LOGITS
     he
    3.77
     він
    3.09
    他
    3.03
     он
    2.92
    He
    2.77
     He
    2.66
    เข
    2.63
     他
    2.39
     তিনি
    2.38
     वह
    2.25
    Activations Density 0.266%

    No Known Activations