© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43095
    Prev
    Next
    INDEX
    Explanations

    pressing, kompressor, Aufgab, osob, yüksek

    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_3_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
     σε
    0.87
    在
    0.85
     في
    0.83
    al
    0.78
     в
    0.77
     ajoute
    0.77
     in
    0.76
     endroit
    0.75
     agate
    0.73
     жана
    0.72
    POSITIVE LOGITS
    AL
    0.91
    (
    0.79
    Bs
    0.77
    Hs
    0.75
    ON
    0.71
    C
    0.71
    V
    0.68
     for
    0.68
    ig
    0.68
    IC
    0.67
    Activations Density 0.025%

    No Known Activations