© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77357
    Prev
    Next
    INDEX
    Explanations

    radius and coordinates calculation

    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
     निर्भर
    0.41
    鈳
    0.38
    ehle
    0.37
     Portion
    0.36
    िवेशन
    0.36
     Bonne
    0.35
    bonne
    0.35
     ক্যান্টনমেন্ট
    0.35
    讴
    0.35
     Heavy
    0.34
    POSITIVE LOGITS
    assembling
    0.35
    Thi
    0.35
    John
    0.34
    Liam
    0.34
    ፆ
    0.34
    Brian
    0.33
    amingo
    0.32
    usages
    0.32
     Dmitri
    0.32
    ೊಂದ
    0.32
    Activations Density 0.002%

    No Known Activations