© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31873
    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_50_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
    зом
    0.39
     பட்ட
    0.39
     trä
    0.38
     sorted
    0.38
    莎
    0.37
    జ్య
    0.37
    ux
    0.36
    оны
    0.36
     ब्राह
    0.36
    vd
    0.35
    POSITIVE LOGITS
    爣
    0.44
     Hayden
    0.42
    Cohen
    0.42
    Dance
    0.42
     émotion
    0.40
     Mosul
    0.40
     yakin
    0.39
    ococci
    0.39
     Cohen
    0.39
     enlev
    0.38
    Activations Density 0.000%

    No Known Activations