© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80652
    Prev
    Next
    INDEX
    Explanations

    poder

    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_0_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
     in
    1.84
    os
    1.82
    es
    1.80
    ing
    1.56
    ول
    1.51
    ة
    1.48
    ab
    1.46
    0
    1.45
    v
    1.42
    ak
    1.41
    POSITIVE LOGITS
    ↵
    1.80
    ки
    1.52
    ו
    1.52
     criticize
    1.49
     conç
    1.48
     moistur
    1.46
     modernize
    1.41
     haue
    1.39
     equalize
    1.39
     authorize
    1.37
    Activations Density 0.000%

    No Known Activations