© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50538
    Prev
    Next
    INDEX
    Explanations

    Google Maps links with coordinates

    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_30_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
    ^{*
    0.32
    这两个
    0.31
    赛事
    0.30
     بتساوي
    0.30
    ））
    0.29
     gamme
    0.29
    两国
    0.29
    rupole
    0.29
     varient
    0.29
    <unused1>
    0.28
    POSITIVE LOGITS
    ্সি
    0.33
    zza
    0.33
    plication
    0.32
    uasion
    0.32
     Commandant
    0.31
    hov
    0.29
     fazla
    0.29
     убе
    0.29
     مقام
    0.29
    فات
    0.29
    Activations Density 0.002%

    No Known Activations