© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80709
    Prev
    Next
    INDEX
    Explanations

    .component.css, .html, .spec.ts

    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_31_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
     обработки
    0.38
     বর্গ
    0.36
    儡
    0.36
     неуда
    0.36
    ICIAL
    0.36
     jazz
    0.35
     parole
    0.35
    Leu
    0.35
    傀
    0.35
     disciplinas
    0.34
    POSITIVE LOGITS
    ндай
    0.41
     Jit
    0.36
     হাসানের
    0.35
     কয়েকজন
    0.35
     প্রতিক্রিয়া
    0.35
     Hasan
    0.35
     হ
    0.34
    兒子
    0.34
     ریس
    0.34
     Renato
    0.33
    Activations Density 0.000%

    No Known Activations