© 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. 222542
    Prev
    Next
    INDEX
    Explanations

    made of

    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
    in
    0.30
    k
    0.29
    ’)
    0.29
    fry
    0.29
    cott
    0.27
    pring
    0.27
    chten
    0.27
    biggest
    0.27
    ق
    0.27
    zhang
    0.27
    POSITIVE LOGITS
     megaphone
    0.30
     an
    0.29
     manipulator
    0.28
    是一种
    0.28
     dirname
    0.27
    مان
    0.27
     pedest
    0.26
     mistress
    0.26
     sab
    0.26
     dispenser
    0.26
    Activations Density 0.005%

    No Known Activations