© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210075
    Prev
    Next
    INDEX
    Explanations

    please paste or provide

    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_20_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
    ᓪ
    0.27
    Vietnam
    0.27
    Behavior
    0.26
     رأس
    0.26
    顷
    0.25
    Bea
    0.25
    Bottom
    0.25
    ونم
    0.24
    娩
    0.24
    ﹌
    0.24
    POSITIVE LOGITS
     novas
    0.30
     neues
    0.30
     новые
    0.29
     nouvelles
    0.28
     Prussians
    0.28
     neuen
    0.28
    িক্স
    0.28
     nuovi
    0.27
     nuovo
    0.27
     ofte
    0.26
    Activations Density 0.008%

    No Known Activations