© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175421
    Prev
    Next
    INDEX
    Explanations

    about/on/addressing followed by noun

    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_20_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
     වර්ග
    0.46
    ijo
    0.43
    俨
    0.42
    ক্টো
    0.42
    fta
    0.42
    pleClass
    0.42
    你也
    0.41
     Apna
    0.40
    yle
    0.40
    <unused29>
    0.39
    POSITIVE LOGITS
     চম
    0.47
     spurred
    0.46
    所謂
    0.46
     exasper
    0.43
    াহত
    0.42
    ᅵ
    0.42
     Regierung
    0.40
    所谓
    0.40
    इसलिए
    0.40
    ﻂ
    0.40
    Activations Density 0.000%

    No Known Activations