© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176437
    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_24_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
     career
    0.51
     sane
    0.47
    UBE
    0.45
     públic
    0.45
     process
    0.44
    日
    0.44
     conserv
    0.43
    UDP
    0.43
    രിച്ചു
    0.43
     chest
    0.42
    POSITIVE LOGITS
     кръ
    0.40
     возник
    0.39
     философ
    0.38
    ناة
    0.38
     לכ
    0.38
     అందు
    0.38
     إلى
    0.38
    ိုလ်
    0.38
     ఉందని
    0.38
     ବ
    0.37
    Activations Density 0.000%

    No Known Activations