© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146529
    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_18_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
    ću
    0.53
    ಹಾಸ
    0.50
    hitth
    0.48
    getpath
    0.47
    ,$$
    0.47
     at
    0.47
     as
    0.47
     sanctuaries
    0.46
     ordinances
    0.46
    개발
    0.46
    POSITIVE LOGITS
    Bright
    0.54
     Conor
    0.53
    ંમે
    0.48
     TextBox
    0.47
     zombie
    0.46
     thai
    0.46
    Urs
    0.46
     karyawan
    0.45
     haemorrh
    0.44
    ﺭ
    0.44
    Activations Density 0.000%

    No Known Activations