© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5191
    Prev
    Next
    INDEX
    Explanations

    simple to more complex

    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_39_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
     ছোট
    0.44
    小さな
    0.39
     तप
    0.38
     சிறிய
    0.38
     छोटी
    0.38
     छोटे
    0.37
    盗
    0.36
     pequeno
    0.36
    减肥
    0.36
     छोटा
    0.36
    POSITIVE LOGITS
     accurate
    0.47
     komplex
    0.41
    ፐ
    0.41
    Ссы
    0.41
     halftime
    0.40
     матч
    0.39
     accur
    0.39
     funkt
    0.39
    伎
    0.39
     comple
    0.38
    Activations Density 0.063%

    No Known Activations