© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93254
    Prev
    Next
    INDEX
    Explanations

    sideways movement

    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_11_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
     서버
    0.60
    SqlClient
    0.60
    핵
    0.59
    SBI
    0.57
    روی
    0.55
    níku
    0.54
    Quanto
    0.53
     روی
    0.53
    Acer
    0.53
    Xiv
    0.52
    POSITIVE LOGITS
    м
    0.59
     Elegant
    0.58
     The
    0.56
    ین
    0.55
     arriving
    0.55
    λα
    0.54
     elegant
    0.54
     Slight
    0.53
     comforted
    0.53
     Paar
    0.53
    Activations Density 0.000%

    No Known Activations