© 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. 78350
    Prev
    Next
    INDEX
    Explanations

    breakdown of sections

    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
     nas
    0.35
    Nas
    0.33
     leve
    0.33
    }`}
    0.32
     stoi
    0.32
     sứ
    0.30
    buc
    0.30
     بط
    0.30
     स्टा
    0.30
     BRIEF
    0.30
    POSITIVE LOGITS
    价
    0.36
     thoát
    0.34
     предотвра
    0.34
    IFS
    0.34
     реаги
    0.34
    確保
    0.34
     Fusion
    0.33
     fusion
    0.32
    Implemented
    0.32
    忽略
    0.32
    Activations Density 0.046%

    No Known Activations