© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8796
    Prev
    Next
    INDEX
    Explanations

    exponentiation or power of 2

    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_40_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
     muster
    0.35
    tilt
    0.35
    một
    0.35
    maxLength
    0.34
     മുത
    0.34
    \&
    0.34
     cốt
    0.33
     whirl
    0.33
     tap
    0.33
    একটি
    0.32
    POSITIVE LOGITS
     ২
    0.52
     TWO
    0.49
     २
    0.48
     Two
    0.47
     Deux
    0.46
    TWO
    0.46
    Two
    0.45
     segunda
    0.45
     δεύτε
    0.45
     two
    0.44
    Activations Density 0.050%

    No Known Activations