© 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. 58728
    Prev
    Next
    INDEX
    Explanations

    backward motion or direction

    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
     μέσω
    0.53
     οποίο
    0.52
     franchises
    0.47
     snatched
    0.47
     y
    0.46
     snatch
    0.45
     финансо
    0.45
     в
    0.44
     размещения
    0.44
     clashes
    0.44
    POSITIVE LOGITS
    ource
    0.53
     Gewicht
    0.53
     重量
    0.52
    적인
    0.50
    }<\
    0.50
    カテゴリー
    0.49
    ट्रोल
    0.48
     بير
    0.48
     Amerikan
    0.47
    বৃদ্ধ
    0.47
    Activations Density 0.110%

    No Known Activations