© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121266
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     고
    0.39
    vanja
    0.38
     హిట్
    0.38
     oprav
    0.38
    vanje
    0.34
     berusia
    0.34
     aree
    0.34
     مقر
    0.34
    瘢
    0.33
    mc
    0.33
    POSITIVE LOGITS
    odon
    0.42
     plenty
    0.42
     listeners
    0.41
     marrying
    0.40
     Runs
    0.40
     performs
    0.39
    odigd
    0.39
     packing
    0.39
     Executes
    0.39
     makes
    0.39
    Activations Density 0.000%

    No Known Activations