© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225589
    Prev
    Next
    INDEX
    Explanations

    Gena Lee Nolin / Carly Rae Jepsen

    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_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
    าน
    0.39
    ก
    0.38
    า
    0.36
     Ueda
    0.36
    ז
    0.35
    1
    0.35
    ק
    0.35
    騫
    0.34
    っ
    0.33
     UC
    0.33
    POSITIVE LOGITS
    ግራ
    0.44
    olines
    0.41
    at
    0.40
     брау
    0.40
    matically
    0.39
    iş
    0.38
    érature
    0.38
    TER
    0.38
     phenomenology
    0.36
     annotated
    0.36
    Activations Density 0.008%

    No Known Activations