© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139704
    Prev
    Next
    INDEX
    Explanations

    console output programming

    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_37_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
     mensagem
    0.40
    amos
    0.40
    drum
    0.39
     compon
    0.39
    refundable
    0.37
    нические
    0.37
    >$
    0.36
     drum
    0.36
    wand
    0.35
    че
    0.35
    POSITIVE LOGITS
     Questionnaire
    0.44
     questionnaire
    0.40
    ştur
    0.40
    造
    0.39
     simplest
    0.39
     questionnaires
    0.39
     subconscious
    0.39
     желу
    0.38
     製造
    0.38
     Procedures
    0.38
    Activations Density 0.001%

    No Known Activations