© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162484
    Prev
    Next
    INDEX
    Explanations

    a description

    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
     săn
    0.38
    رسی
    0.37
     نز
    0.37
     أص
    0.36
    افة
    0.35
     Unterstützung
    0.35
    ピュー
    0.35
    烦
    0.35
     budgeted
    0.34
     పూర్తి
    0.34
    POSITIVE LOGITS
     individual
    0.42
    intuitive
    0.41
     devastated
    0.40
     humiliated
    0.39
    individual
    0.38
     hypot
    0.36
     steadfast
    0.36
     அழைக்க
    0.36
     wanting
    0.36
     Bernhard
    0.35
    Activations Density 0.002%

    No Known Activations