© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237887
    Prev
    Next
    INDEX
    Explanations

    numbers and units, percentages, quantities

    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_32_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
     less
    0.39
     riport
    0.37
    においては
    0.37
     increases
    0.36
    における
    0.36
    通
    0.36
    佔
    0.36
    ux
    0.36
    占
    0.35
     í
    0.35
    POSITIVE LOGITS
    ALTERNATIV
    0.41
     Estr
    0.41
     तिवारी
    0.39
    टीना
    0.39
    乆
    0.38
     জিজ্ঞ
    0.38
    𒁾
    0.37
     डेंगू
    0.37
    ্দি
    0.37
    री
    0.37
    Activations Density 0.000%

    No Known Activations