© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45203
    Prev
    Next
    INDEX
    Explanations

    fabric of spacetime

    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_13_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
     very
    0.42
    nless
    0.41
    ้าน
    0.40
    川
    0.38
     কলকাতার
    0.38
     Very
    0.38
    Very
    0.38
     راحت
    0.37
    ぁ
    0.37
    very
    0.36
    POSITIVE LOGITS
    โท
    0.45
    üle
    0.43
     Uri
    0.41
    Укра
    0.40
    ässig
    0.39
     depois
    0.39
     Daarna
    0.38
     aspekt
    0.38
     Уен
    0.38
     Mexiko
    0.38
    Activations Density 0.056%

    No Known Activations