© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175432
    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_20_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
     கடல்
    0.45
    摽
    0.44
    婹
    0.44
    zeptember
    0.44
    势
    0.44
    梩
    0.44
    ATURE
    0.43
     upstate
    0.43
    凊
    0.43
    季節
    0.42
    POSITIVE LOGITS
     Saif
    0.44
    هل
    0.43
     Oils
    0.43
     Saul
    0.42
     שני
    0.42
     টাক
    0.41
     blockchain
    0.41
     Anil
    0.41
    બ
    0.40
     हालांकि
    0.39
    Activations Density 0.000%

    No Known Activations