© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116842
    Prev
    Next
    INDEX
    Explanations

    service is

    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_27_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
     Jésus
    0.28
    ತೆಗೆ
    0.28
    ৃতা
    0.28
     दिखाने
    0.28
     ब्रो
    0.28
     बनाए
    0.27
     proclaim
    0.27
    ✠
    0.27
    äische
    0.27
    த்ரே
    0.27
    POSITIVE LOGITS
    Quantity
    0.29
     داخل
    0.28
    Indent
    0.28
    QQ
    0.27
    耑
    0.27
    Fee
    0.27
     سل
    0.27
     Verbindung
    0.27
     بى
    0.26
    Optimize
    0.26
    Activations Density 0.003%

    No Known Activations