© 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. 2697
    Prev
    Next
    INDEX
    Explanations

    dialogue beginnings

    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
    攪
    0.39
    }"),
    0.38
    lini
    0.35
    şı
    0.35
    inhib
    0.35
    Inform
    0.35
    哈
    0.35
    und
    0.35
    ([-
    0.35
     ഇപ്പോള്‍
    0.35
    POSITIVE LOGITS
     jendela
    0.41
     действие
    0.41
    ReturnValue
    0.40
    getAction
    0.40
     window
    0.38
     ventana
    0.38
    窗
    0.38
    臬
    0.37
     WINDOW
    0.37
    WindowManager
    0.37
    Activations Density 0.002%

    No Known Activations