© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205590
    Prev
    Next
    INDEX
    Explanations

    say position

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     $^{
    0.48
     $^{\
    0.46
    প্রবাসী
    0.41
     pr
    0.40
     $_{
    0.38
     astonished
    0.38
     pessimistic
    0.37
     пой
    0.37
    Volatility
    0.37
    
    0.36
    POSITIVE LOGITS
     post
    0.61
    post
    0.56
     Post
    0.50
    Post
    0.50
     posicion
    0.49
     positioning
    0.47
     пост
    0.47
     postwar
    0.45
    position
    0.43
    positioned
    0.43
    Activations Density 0.002%

    No Known Activations