© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140044
    Prev
    Next
    INDEX
    Explanations

    OpenAPI specifications and documentation

    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_12_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
     ทอง
    0.55
     tuku
    0.54
    釹
    0.54
     lunar
    0.53
     steward
    0.53
    รียม
    0.52
     draper
    0.52
     sh
    0.52
     vend
    0.52
     shameful
    0.51
    POSITIVE LOGITS
    Last
    0.51
    at
    0.50
    0
    0.49
    function
    0.49
    im
    0.48
    it
    0.47
    Your
    0.45
    بعد
    0.45
    n
    0.45
    After
    0.45
    Activations Density 0.000%

    No Known Activations