© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198461
    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_9_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
    黃
    0.52
    Protect
    0.51
    أ
    0.51
    Professional
    0.48
     protect
    0.47
    מע
    0.47
     ver
    0.47
    Industrial
    0.47
    الإ
    0.45
    ﺑ
    0.45
    POSITIVE LOGITS
    gada
    0.55
     Panchayat
    0.55
     Oogie
    0.53
    sendKeyDown
    0.53
     CCSDT
    0.52
     samano
    0.51
    żenia
    0.50
     Lohia
    0.50
     Cáceres
    0.50
     Dioxide
    0.49
    Activations Density 0.000%

    No Known Activations