© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198365
    Prev
    Next
    INDEX
    Explanations

    Gemma

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     seater
    0.40
     cubed
    0.40
     Ronald
    0.39
     깔
    0.39
    黟
    0.39
    Ronald
    0.37
    ್ಯ
    0.35
     topper
    0.35
     Na
    0.35
     cube
    0.35
    POSITIVE LOGITS
    inim
    0.46
    inburgh
    0.43
    Txt
    0.41
     স্বর্ণ
    0.41
    𝚓
    0.39
    aison
    0.39
    文本
    0.39
    কিন
    0.39
     मांसपेश
    0.38
    ijska
    0.38
    Activations Density 0.006%

    No Known Activations