© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2882
    Prev
    Next
    INDEX
    Explanations

    manifest.json

    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_40_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
     born
    0.40
     borne
    0.40
    Born
    0.39
    誉
    0.39
    born
    0.38
    dew
    0.37
     transformer
    0.37
    ઠ
    0.36
     Transformer
    0.35
     transformar
    0.35
    POSITIVE LOGITS
    ِمض
    0.39
     ******
    0.37
     *****
    0.35
     بیټینګ
    0.34
    েইলি
    0.34
     پڑھیئے
    0.34
    ّم
    0.33
    ۆی
    0.33
     Dent
    0.33
     ഏറ്റ
    0.33
    Activations Density 0.002%

    No Known Activations