© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176130
    Prev
    Next
    INDEX
    Explanations

    story begins

    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_24_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
     constituye
    0.42
    
    0.40
     женой
    0.39
    丞
    0.39
    delay
    0.39
    swith
    0.39
    longer
    0.38
     została
    0.38
    acje
    0.38
    mayı
    0.37
    POSITIVE LOGITS
    輸出
    0.41
     invers
    0.38
     vér
    0.38
    实用
    0.38
    输
    0.38
    ActionResult
    0.37
     Marxism
    0.36
    ಿಂದ
    0.36
     ઉપયોગ
    0.36
     입력
    0.35
    Activations Density 0.002%

    No Known Activations