© 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. 35650
    Prev
    Next
    INDEX
    Explanations

    HTML code structure

    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
    住
    0.52
     living
    0.51
     resides
    0.50
    居住
    0.49
    住在
    0.48
     viviendo
    0.48
     বসবাস
    0.44
     жить
    0.44
     живе
    0.44
     reside
    0.43
    POSITIVE LOGITS
    ړئ
    0.42
    <?=
    0.39
    bright
    0.36
    ัฐ
    0.36
    unz
    0.36
    Comment
    0.35
    Coming
    0.35
     fprintf
    0.35
     deng
    0.34
    mc
    0.34
    Activations Density 0.001%

    No Known Activations