© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193921
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    ുട
    0.41
     أو
    0.41
    ak
    0.40
    وية
    0.40
    ilateral
    0.40
    jz
    0.40
    tek
    0.40
    e
    0.40
     Sc
    0.39
     الأصل
    0.39
    POSITIVE LOGITS
    nameSort
    0.42
     gpio
    0.40
     сын
    0.39
    GD
    0.38
     BAFF
    0.38
     newMessage
    0.38
    筍
    0.37
     സാഹ
    0.37
     rafts
    0.37
     asleep
    0.37
    Activations Density 0.000%

    No Known Activations