© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36993
    Prev
    Next
    INDEX
    Explanations

    explains you / your situation

    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_11_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
     continúa
    0.57
     他们
    0.51
     correspondió
    0.50
     他
    0.49
     وكانت
    0.49
     通过
    0.48
     comienza
    0.48
     cleats
    0.48
     entró
    0.48
     موسي
    0.48
    POSITIVE LOGITS
    f
    0.51
    ר
    0.50
     yh
    0.50
    و
    0.46
    ۰
    0.46
     टे
    0.46
    ینی
    0.46
    ס
    0.46
    ään
    0.45
    愆
    0.45
    Activations Density 0.014%

    No Known Activations