© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25241
    Prev
    Next
    INDEX
    Explanations

    Sci-Fi

    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_10_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
    ლებ
    0.63
    诘
    0.58
     strands
    0.56
    ಗಳು
    0.55
     insulating
    0.55
     surpluses
    0.54
    nashvillehousing
    0.54
    ɕ
    0.52
    zę
    0.52
     countertops
    0.52
    POSITIVE LOGITS
     использова
    0.61
     druge
    0.58
    電影
    0.57
     sistemi
    0.56
     поез
    0.56
     Dome
    0.56
    നിന്ന്
    0.56
     danni
    0.55
     duas
    0.54
     get
    0.54
    Activations Density 0.000%

    No Known Activations