© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61883
    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_11_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
     Accommodation
    0.50
    ť
    0.49
     Copy
    0.49
     Ideally
    0.48
     Accessible
    0.48
     Depreciation
    0.47
     Logs
    0.47
    S
    0.47
     Pastoral
    0.46
     Files
    0.46
    POSITIVE LOGITS
    逮捕
    0.47
    Goss
    0.45
     compounded
    0.43
    ರ
    0.42
    arrest
    0.42
    ftar
    0.42
    脂
    0.42
    layered
    0.41
    paced
    0.41
    FRED
    0.41
    Activations Density 0.000%

    No Known Activations