© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10126
    Prev
    Next
    INDEX
    Explanations

    airspace, innocent passage, targets, claims, virtual machine

    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_13_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
    Python
    0.12
    t
    0.12
     असतात
    0.11
    ☮
    0.11
     embry
    0.11
     WordPress
    0.11
    溦
    0.10
    WMat
    0.10
     美国
    0.10
     Maharashtra
    0.10
    POSITIVE LOGITS
    established
    0.12
    є
    0.11
     তিক্ত
    0.11
     directeur
    0.11
     didn
    0.11
    ей
    0.11
    elipe
    0.11
    тельного
    0.11
    bew
    0.11
    implies
    0.10
    Activations Density 0.013%

    No Known Activations