© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245702
    Prev
    Next
    INDEX
    Explanations

    decorator, function, transforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_11_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
     Urb
    0.67
    Clique
    0.60
    식
    0.59
    ុស
    0.59
     emblem
    0.59
     mecan
    0.58
     squad
    0.58
     اتر
    0.56
     windshield
    0.56
     brav
    0.56
    POSITIVE LOGITS
     القرآن
    0.70
    喜び
    0.67
     ऑयल
    0.67
     Tidak
    0.64
    不再
    0.63
     türlü
    0.63
    ᾷ
    0.62
     अपन
    0.61
    红
    0.61
    appreci
    0.61
    Activations Density 0.008%

    No Known Activations