© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90796
    Prev
    Next
    INDEX
    Explanations

    carriages, misclassifying

    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_3_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
    i
    0.79
    ić
    0.67
    י
    0.65
    at
    0.62
    ant
    0.61
    iato
    0.61
    s
    0.59
    inį
    0.59
     for
    0.59
     summaries
    0.58
    POSITIVE LOGITS
    のは
    0.68
    ку
    0.66
    υ
    0.65
    료
    0.64
     Barcelone
    0.61
    Tree
    0.61
    ח
    0.61
     दो
    0.60
     has
    0.59
    і
    0.59
    Activations Density 0.000%

    No Known Activations