© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77363
    Prev
    Next
    INDEX
    Explanations

    Microsoft Office applications

    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
    👂
    0.40
     الصوت
    0.39
     transmissão
    0.37
     лам
    0.37
    REL
    0.36
     UIView
    0.36
     носи
    0.36
    Wrist
    0.36
    WebView
    0.35
     complication
    0.35
    POSITIVE LOGITS
    arket
    0.39
    噁
    0.39
    uettes
    0.38
     vostro
    0.38
     manut
    0.38
    падает
    0.37
     exploiting
    0.37
     align
    0.37
     городской
    0.36
    ลงทุน
    0.36
    Activations Density 0.010%

    No Known Activations