© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130832
    Prev
    Next
    INDEX
    Explanations

    unusual tokens

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     verb
    0.41
     vali
    0.40
    =====
    0.39
     wrestled
    0.39
     ساک
    0.39
     Sac
    0.38
     Alegre
    0.36
     wellness
    0.36
    ******
    0.36
    `-
    0.36
    POSITIVE LOGITS
     basilaires
    0.38
     निर
    0.37
    reducers
    0.37
    etse
    0.37
    تماد
    0.37
    zá
    0.37
    閂
    0.36
    ivatives
    0.36
    RAIT
    0.36
     conforming
    0.36
    Activations Density 0.001%

    No Known Activations