© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211044
    Prev
    Next
    INDEX
    Explanations

    calculation, skills, depth

    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_19_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
    ப்
    0.46
    ант
    0.46
    บริเวณ
    0.45
     기
    0.44
     undercut
    0.44
    TaskPojo
    0.43
     ዋና
    0.43
    Btn
    0.42
     bluish
    0.42
     sweat
    0.42
    POSITIVE LOGITS
    বয়
    0.56
    বয়
    0.54
    歲
    0.52
     रिले
    0.48
    纍
    0.47
    مثل
    0.46
    house
    0.46
    records
    0.46
    ponde
    0.45
    យើង
    0.44
    Activations Density 0.000%

    No Known Activations