© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168803
    Prev
    Next
    INDEX
    Explanations

    low or reduced

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ни
    2.22
     ni
    1.95
     ní
    1.72
     Ni
    1.68
    Ni
    1.57
     NI
    1.49
     Ни
    1.43
    ニ
    1.42
     니
    1.38
    ni
    1.38
    POSITIVE LOGITS
     lower
    0.73
    lower
    0.72
    Lower
    0.71
     Lower
    0.67
     LOWER
    0.61
    reduced
    0.60
     कम
    0.58
     reduced
    0.53
    Reduced
    0.52
     Reduced
    0.49
    Activations Density 0.004%

    No Known Activations