© 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. 120065
    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
    互動
    0.43
     cải
    0.42
    族的
    0.41
    族
    0.40
    朗
    0.40
    通常の
    0.40
    Android
    0.40
    莎
    0.40
    LG
    0.38
     মুনা
    0.38
    POSITIVE LOGITS
     testament
    0.43
     Peter
    0.41
     represent
    0.40
    닛
    0.39
     testimony
    0.39
     bony
    0.38
     Stephen
    0.37
     Lewis
    0.37
     Peyton
    0.37
     Poj
    0.37
    Activations Density 0.000%

    No Known Activations