© 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-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52013
    Prev
    Next
    INDEX
    Explanations

    the

    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_55_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
     closing
    0.49
    closing
    0.47
    Closing
    0.45
     Closing
    0.44
     Bezeichnung
    0.43
    ;</
    0.39
    月份
    0.38
    ();
    0.38
     top
    0.37
     टाक
    0.37
    POSITIVE LOGITS
     നേര
    0.43
    当初
    0.42
    OnError
    0.41
    ByDefault
    0.40
     `-
    0.38
     tidigare
    0.37
     sebelumnya
    0.36
     originalmente
    0.36
    inicial
    0.36
     inaugural
    0.35
    Activations Density 0.003%

    No Known Activations