© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135614
    Prev
    Next
    INDEX
    Explanations

    reducing model uncertainty

    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_37_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
    𠄌
    0.44
    শ্ত
    0.43
     JPG
    0.42
    panel
    0.41
     جمہوری
    0.41
     Ing
    0.39
     Efficiency
    0.39
    蠹
    0.39
     Shir
    0.39
     iglesia
    0.39
    POSITIVE LOGITS
    constraint
    0.44
     Uncertainty
    0.41
    isel
    0.40
     Constraint
    0.39
    constraints
    0.39
     Improving
    0.38
     uncertainty
    0.38
     improving
    0.37
    実験
    0.37
     reconstructions
    0.36
    Activations Density 0.001%

    No Known Activations