© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28068
    Prev
    Next
    INDEX
    Explanations

    train tracks

    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_10_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
    OneDrive
    0.52
    济
    0.51
    戴
    0.50
    ד
    0.48
    авто
    0.47
    主
    0.47
    мед
    0.47
    磨
    0.47
    섭
    0.47
    He
    0.47
    POSITIVE LOGITS
     x
    0.60
     lancio
    0.58
     eighth
    0.55
     ฉาก
    0.52
     lanza
    0.52
     while
    0.51
     laag
    0.51
     followed
    0.50
     largeur
    0.50
     momento
    0.50
    Activations Density 0.000%

    No Known Activations