© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125466
    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_37_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
    ธ์
    0.39
     Constructs
    0.38
    TypeScript
    0.38
    assing
    0.38
    시
    0.36
     sheet
    0.35
    sheet
    0.35
    usi
    0.35
    entro
    0.35
    علان
    0.35
    POSITIVE LOGITS
    रखाव
    0.43
     nahezu
    0.40
     паліты
    0.39
    ^{*}(
    0.39
    Dynamic
    0.38
    وست
    0.38
    лювання
    0.38
     discharged
    0.36
    itchie
    0.36
    `],
    0.35
    Activations Density 0.000%

    No Known Activations