© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176987
    Prev
    Next
    INDEX
    Explanations

    气

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     falling
    0.42
     scrape
    0.42
     ग
    0.40
    يج
    0.40
     Falling
    0.40
    しゃ
    0.39
    igita
    0.39
    ig
    0.39
     oes
    0.39
    িগ
    0.39
    POSITIVE LOGITS
    便利
    0.41
    門
    0.40
    ⺊
    0.39
    DialogFragment
    0.37
    门
    0.36
     الطب
    0.36
    ன்ஸ்
    0.36
    限制
    0.36
    机会
    0.35
    న్స్
    0.35
    Activations Density 0.000%

    No Known Activations