© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51190
    Prev
    Next
    INDEX
    Explanations

    common examples

    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_30_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
    ٰی
    0.36
    ிகள்
    0.35
    どの
    0.33
    、『
    0.33
    一つの
    0.33
    ofa
    0.32
    रेक्ट
    0.32
    teries
    0.32
    ⵎ
    0.31
    的一個
    0.31
    POSITIVE LOGITS
     cruise
    0.37
     Cruise
    0.36
     сек
    0.33
     visitante
    0.33
     sys
    0.32
     lok
    0.32
    рата
    0.32
    isVideoRecording
    0.31
     macchina
    0.31
     ordinateur
    0.31
    Activations Density 0.016%

    No Known Activations