© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5637
    Prev
    Next
    INDEX
    Explanations

    control and 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_39_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
    าลัย
    0.37
     brilliant
    0.36
     возбу
    0.36
    ข
    0.35
    زد
    0.34
     ассорти
    0.34
     bankrupt
    0.34
    ยว
    0.34
    Evaluation
    0.34
    ्यता
    0.33
    POSITIVE LOGITS
    ≳
    0.41
    imiya
    0.41
    pressed
    0.41
    lii
    0.40
    辟
    0.39
    mack
    0.39
    鹛
    0.38
    UIControl
    0.38
    رير
    0.37
    ≒
    0.36
    Activations Density 0.078%

    No Known Activations