© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88671
    Prev
    Next
    INDEX
    Explanations

    solar wind radiation flares

    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_23_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
     ضرورت
    0.42
    irtschaft
    0.40
    Fleet
    0.40
    轂
    0.40
    Economic
    0.39
    ویز
    0.39
    經濟
    0.39
    畈
    0.39
    ยก
    0.39
     رع
    0.39
    POSITIVE LOGITS
     debat
    0.50
     grime
    0.49
     sketches
    0.48
     biochemistry
    0.45
     nast
    0.43
     sketch
    0.43
     desorption
    0.43
     bud
    0.43
     biomarker
    0.43
     selfie
    0.43
    Activations Density 0.003%

    No Known Activations