© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18014
    Prev
    Next
    INDEX
    Explanations

    American Revolution historical figures

    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_40_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
    Constitution
    0.44
    constitution
    0.41
     Constitution
    0.41
     constitution
    0.40
     carnivorous
    0.38
    夗
    0.37
    淋
    0.37
    Ⴚ
    0.37
     ప్రశ్
    0.37
     aneurysm
    0.36
    POSITIVE LOGITS
    serializers
    0.38
    丁
    0.34
     올
    0.34
    దు
    0.33
     nú
    0.33
    Giz
    0.33
    rédients
    0.32
     البنات
    0.32
    icans
    0.32
    expires
    0.32
    Activations Density 0.041%

    No Known Activations