© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207549
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
     större
    0.48
    étais
    0.43
    šen
    0.41
     भने
    0.41
     begleitet
    0.41
    पुट
    0.41
    etas
    0.40
    劈
    0.40
    衅
    0.40
    sonsten
    0.40
    POSITIVE LOGITS
     J
    0.55
     H
    0.50
    j
    0.50
    रीन
    0.49
    in
    0.49
     договор
    0.49
    জ
    0.49
    kJ
    0.47
     sustainably
    0.46
    ลงทุน
    0.46
    Activations Density 0.000%

    No Known Activations