© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132624
    Prev
    Next
    INDEX
    Explanations

    resource leaks

    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_6_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
     it
    0.70
     l
    0.69
     $\
    0.67
     to
    0.65
     i
    0.63
     $
    0.61
     you
    0.59
     I
    0.58
     vodka
    0.58
     Information
    0.56
    POSITIVE LOGITS
    d
    0.79
    ба
    0.68
    dür
    0.63
    ২
    0.62
    ด
    0.60
    ৬
    0.60
    دی
    0.59
    РА
    0.59
    dari
    0.57
    ТИ
    0.57
    Activations Density 0.001%

    No Known Activations