© 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. 207206
    Prev
    Next
    INDEX
    Explanations

    Company Description

    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
    ,
    0.56
    Quiet
    0.54
    irl
    0.51
    cks
    0.50
    TL
    0.49
     =
    0.48
     initi
    0.48
    SIAN
    0.48
    ודי
    0.47
    form
    0.46
    POSITIVE LOGITS
    パーカー
    0.61
     Alberta
    0.58
    ৫
    0.58
     NIKE
    0.58
    പ്
    0.57
     {}>,
    0.57
     ojo
    0.56
     शुक्रिया
    0.55
    te
    0.55
     アウター
    0.55
    Activations Density 0.000%

    No Known Activations