© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44720
    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_22_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
    getZoom
    0.47
    thisTrack
    0.47
    ՜
    0.46
     nettement
    0.46
    trashItem
    0.45
    ുകൊ
    0.45
    ниці
    0.44
    ak
    0.43
     Tattha
    0.43
     inactivació
    0.43
    POSITIVE LOGITS
    Č
    0.49
    logo
    0.48
     (
    0.46
    Logo
    0.45
     on
    0.43
    Screens
    0.43
     direção
    0.43
    到
    0.43
    畯
    0.43
    S
    0.42
    Activations Density 0.000%

    No Known Activations