© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216941
    Prev
    Next
    INDEX
    Explanations

    fact-checking websites and organizations

    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_31_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
    高品質
    0.41
     hypogly
    0.36
     bacterial
    0.36
    捶
    0.36
     hypergly
    0.35
    叐
    0.35
     advising
    0.34
    糖尿病
    0.34
     haemorrh
    0.34
    浼
    0.34
    POSITIVE LOGITS
     Provisions
    0.35
    metals
    0.35
    centage
    0.34
    ch
    0.34
    uki
    0.33
     Verify
    0.33
     নিতান্ত
    0.33
    ike
    0.33
    inar
    0.33
     Reasonable
    0.33
    Activations Density 0.001%

    No Known Activations