© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16604
    Prev
    Next
    INDEX
    Explanations

    treaties and historical unions

    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
    ('../
    0.39
    ভারতীয়
    0.39
     Commissary
    0.39
    ('\
    0.38
     Somali
    0.37
    லான
    0.37
    Sb
    0.36
    كب
    0.36
    ('#
    0.36
    交
    0.36
    POSITIVE LOGITS
     Fontainebleau
    0.44
     TREAT
    0.40
    Rug
    0.40
     extremes
    0.38
    treat
    0.38
    Treat
    0.38
    ोटा
    0.37
     Greenville
    0.37
     Rug
    0.36
    رياض
    0.36
    Activations Density 0.021%

    No Known Activations