© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59066
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    *
    0.45
    ദ്യോഗ
    0.37
    <strong>
    0.37
    |");
    0.36
    சிக்கும்
    0.35
     destinée
    0.35
     destinada
    0.35
     courtroom
    0.35
     destinado
    0.35
    
    0.35
    POSITIVE LOGITS
     ۹
    0.43
     ৯
    0.43
    esh
    0.40
    ↵
    0.40
     ২৯
    0.38
     १३
    0.38
    impulan
    0.37
     ۱۳
    0.37
     ܀
    0.36
     ა
    0.36
    Activations Density 0.018%

    No Known Activations