© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166408
    Prev
    Next
    INDEX
    Explanations

    Kurdish and Somali regions

    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_31_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
    Almost
    0.31
    Appro
    0.31
     Apro
    0.31
    牛奶
    0.30
     Docsity
    0.30
    𝒜
    0.30
     dů
    0.29
     Zuf
    0.29
    吃
    0.29
    暏
    0.29
    POSITIVE LOGITS
    oshop
    0.31
    Franklin
    0.30
    ואה
    0.30
     gle
    0.30
    निक
    0.30
     Franklin
    0.29
    bal
    0.29
     nik
    0.29
    નિક
    0.29
    ocole
    0.29
    Activations Density 0.001%

    No Known Activations