© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58446
    Prev
    Next
    INDEX
    Explanations

    Spanish/German word fragments; Spanish/German words

    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_2_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
    ن
    1.48
    ل
    1.22
    ή
    1.21
    ियों
    1.11
    ח
    1.08
    म
    1.06
    ى
    1.05
    ம்
    0.99
    kör
    0.98
    ون
    0.98
    POSITIVE LOGITS
     is
    1.20
    1.19
     are
    1.09
     comedian
    1.06
     can
    1.05
     heeft
    1.05
     پیسو
    0.99
    ATING
    0.98
     will
    0.96
     தொடர்பான
    0.96
    Activations Density 0.000%

    No Known Activations