© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234359
    Prev
    Next
    INDEX
    Explanations

    decimal formatting

    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_32_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
    作为一个
    0.41
     因为
    0.37
    잊
    0.37
    ীকরণ
    0.37
    PUS
    0.37
     Oph
    0.36
     Н
    0.35
    Су
    0.35
    soluble
    0.35
    대한
    0.34
    POSITIVE LOGITS
     spending
    0.41
     backs
    0.39
     winters
    0.39
     flower
    0.38
     retrie
    0.37
     unlike
    0.37
     flowers
    0.36
     mustang
    0.35
     advises
    0.35
    চলে
    0.35
    Activations Density 0.001%

    No Known Activations