© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216082
    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_31_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
     dihasil
    0.43
    脛
    0.40
    顎
    0.39
    ỷ
    0.39
    読んで
    0.37
     വായി
    0.36
     پانچ
    0.36
    歙
    0.36
    Summary
    0.35
     ಅಮ
    0.35
    POSITIVE LOGITS
     answered
    0.39
     answers
    0.37
    茬
    0.37
     thrill
    0.36
     enthusiasm
    0.34
     answer
    0.34
     plaintext
    0.33
    ।*
    0.33
     groom
    0.33
     thermost
    0.32
    Activations Density 0.000%

    No Known Activations