© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40900
    Prev
    Next
    INDEX
    Explanations

    analog-to-digital converters

    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_11_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
    แหล่ง
    0.51
    ोरा
    0.50
    ă
    0.50
     футболка
    0.49
    មាន
    0.48
     interessante
    0.48
    ի
    0.48
    好奇
    0.48
     Brawl
    0.48
     ⭐
    0.47
    POSITIVE LOGITS
    ර්
    0.59
    साब
    0.58
    ity
    0.54
    ورت
    0.53
    ﻻ
    0.53
     conceptual
    0.52
     Texte
    0.52
     cuatro
    0.52
    עי
    0.52
    ータル
    0.52
    Activations Density 0.003%

    No Known Activations