© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 638
    Prev
    Next
    INDEX
    Explanations

    publicly available

    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_44_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
    シート
    0.38
    pregnant
    0.37
    🤢
    0.37
     Sick
    0.36
    ป่วย
    0.36
    sick
    0.35
    стен
    0.35
    จะต้อง
    0.35
    thunder
    0.35
    Sick
    0.35
    POSITIVE LOGITS
     Maximal
    0.38
     ре
    0.37
     recoup
    0.36
    짊
    0.36
     Hahn
    0.36
    ႏ
    0.36
    ước
    0.35
     engag
    0.35
     Age
    0.35
    奇
    0.35
    Activations Density 0.030%

    No Known Activations