© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236586
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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_46_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
    વાર
    0.40
    zenia
    0.39
    শিক
    0.39
    FileNotFound
    0.38
     खि
    0.37
    ²)
    0.37
     Dev
    0.36
     Mini
    0.36
     Mori
    0.36
    physema
    0.36
    POSITIVE LOGITS
    劵
    0.47
    คู่
    0.39
    obs
    0.39
     सर्
    0.37
    lords
    0.37
    Lime
    0.37
    Mango
    0.37
    B
    0.36
     বই
    0.36
    éci
    0.36
    Activations Density 0.009%

    No Known Activations