© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201047
    Prev
    Next
    INDEX
    Explanations

    OED or Oedipus

    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_6_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
    of
    1.20
    m
    0.96
    ofthe
    0.95
     mikä
    0.87
     první
    0.79
     bolj
    0.74
     वाइज
    0.73
    3
    0.73
     dhinak
    0.73
    𝟯
    0.73
    POSITIVE LOGITS
    د
    1.14
    ל
    1.05
     is
    1.05
    ه
    1.04
    t
    1.02
    ק
    0.99
    ان
    0.93
    س
    0.88
    র
    0.87
    iss
    0.87
    Activations Density 0.000%

    No Known Activations