© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58178
    Prev
    Next
    INDEX
    Explanations

    le ne

    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_59_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
     তারা
    0.53
     они
    0.45
     他们
    0.44
     তারাও
    0.42
    他們
    0.41
    তারা
    0.39
     вони
    0.39
    짱
    0.39
    他们
    0.39
     તેઓ
    0.39
    POSITIVE LOGITS
    le
    1.48
    ле
    0.94
    ले
    0.84
     le
    0.74
    ne
    0.73
    เล
    0.70
    লে
    0.66
    Ле
    0.66
    üle
    0.64
    LE
    0.64
    Activations Density 0.017%

    No Known Activations