© 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. 44826
    Prev
    Next
    INDEX
    Explanations

    content creators

    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
     to
    0.78
    ps
    0.76
    ست
    0.75
    م
    0.70
    to
    0.68
    pg
    0.66
    press
    0.64
    pos
    0.62
    te
    0.62
    pass
    0.61
    POSITIVE LOGITS
    ມີ
    0.63
    دين
    0.63
    \}=\
    0.62
    ום
    0.59
     entspre
    0.58
    ဖြစ်
    0.57
    $
    0.57
    മായ
    0.57
     subparagraph
    0.56
    וף
    0.56
    Activations Density 0.012%

    No Known Activations