© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125347
    Prev
    Next
    INDEX
    Explanations

    before, then action

    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_37_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
     mengambil
    0.42
    zeichnet
    0.37
     aportar
    0.37
    跟着
    0.36
     reinst
    0.36
    輋
    0.36
     taking
    0.36
     removing
    0.35
    쟈
    0.35
     entrando
    0.35
    POSITIVE LOGITS
     любом
    0.44
    meets
    0.39
    воз
    0.38
     cualquier
    0.37
    Anything
    0.37
     любого
    0.37
     কাহারও
    0.37
     любые
    0.37
    uração
    0.36
    кости
    0.36
    Activations Density 0.009%

    No Known Activations