© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13384
    Prev
    Next
    INDEX
    Explanations

    Hitchhiker's Guide to the Galaxy

    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_40_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
    getSystemService
    0.41
    ﺧ
    0.41
    爻
    0.41
    άζ
    0.37
    Innovation
    0.36
     étoiles
    0.36
    DTD
    0.36
     பு
    0.36
    反应
    0.36
    Hours
    0.35
    POSITIVE LOGITS
     maths
    0.41
    GroupBy
    0.40
     počíta
    0.39
     dogs
    0.39
     grou
    0.39
     perros
    0.39
    禽
    0.39
     সানডে
    0.39
    computers
    0.38
     फसलों
    0.38
    Activations Density 0.006%

    No Known Activations