© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151326
    Prev
    Next
    INDEX
    Explanations

    problems

    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_59_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
    <unused86>
    0.41
    椒
    0.41
    zam
    0.40
     Probation
    0.39
    <unused36>
    0.39
    zas
    0.39
    ৃতা
    0.38
     Probab
    0.38
     项
    0.38
    ichage
    0.37
    POSITIVE LOGITS
     issue
    1.91
     issues
    1.67
    Issue
    1.63
     Issue
    1.61
    issue
    1.60
     Issues
    1.50
    Issues
    1.49
    issues
    1.45
     vấn
    1.23
     problems
    1.15
    Activations Density 0.001%

    No Known Activations