© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3500
    Prev
    Next
    INDEX
    Explanations

    global/en/

    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_39_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
     long
    0.42
     Hinter
    0.41
     Long
    0.40
     popular
    0.39
     UEFI
    0.39
     keber
    0.39
     inductive
    0.37
     "
    0.37
    ppes
    0.37
     Vogue
    0.37
    POSITIVE LOGITS
    දය
    0.40
     violators
    0.38
    Qualified
    0.38
    arts
    0.37
    لز
    0.35
     کامیابی
    0.35
    itsch
    0.35
     квали
    0.34
     isomorphisms
    0.34
    ARTS
    0.34
    Activations Density 0.001%

    No Known Activations