© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35066
    Prev
    Next
    INDEX
    Explanations

    kan

    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_50_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
     U
    0.56
    Fut
    0.49
     фу
    0.48
     URANIUM
    0.48
    U
    0.47
     JAS
    0.46
     Fuk
    0.46
     Fut
    0.46
    福
    0.45
     fut
    0.44
    POSITIVE LOGITS
     N
    0.50
     Кана
    0.46
     canadian
    0.42
    akan
    0.42
    Kenny
    0.41
     Ham
    0.41
     Kann
    0.39
    廉
    0.39
    ığın
    0.39
     कामा
    0.38
    Activations Density 0.010%

    No Known Activations