© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1628
    Prev
    Next
    INDEX
    Explanations

    determining the severity, stage, or presence

    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_39_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
     Leistungs
    0.35
    =\{\
    0.35
    joins
    0.35
    performs
    0.34
     حقیقی
    0.34
    TARGET
    0.33
     advantageous
    0.33
     Stocks
    0.33
     अके
    0.33
    㚅
    0.33
    POSITIVE LOGITS
     Professor
    0.38
     stage
    0.36
     đạo
    0.35
     प्रोफेसर
    0.35
    统
    0.35
    免疫
    0.35
    סה
    0.35
     auto
    0.35
     flood
    0.34
     veden
    0.34
    Activations Density 0.068%

    No Known Activations