© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220422
    Prev
    Next
    INDEX
    Explanations

    makes it easy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    Visible
    0.34
    functions
    0.31
    钯
    0.30
     bol
    0.29
     dim
    0.29
    network
    0.29
    held
    0.29
     simply
    0.29
    Simply
    0.29
     visibly
    0.29
    POSITIVE LOGITS
     revolutionaries
    0.30
    کرو
    0.29
     crossovers
    0.29
     Surveyor
    0.29
    tg
    0.28
     Ekonom
    0.28
    ~/
    0.28
     kwamba
    0.28
    উত্তরঃ
    0.27
     proverbial
    0.27
    Activations Density 0.004%

    No Known Activations