© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209597
    Prev
    Next
    INDEX
    Explanations

    prime minister names

    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_20_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
     cultivation
    0.40
    ambo
    0.39
     erm
    0.39
     Phenomenology
    0.38
     theologian
    0.38
    慎
    0.38
    诤
    0.38
    OLOG
    0.38
     زید
    0.37
     wickedness
    0.37
    POSITIVE LOGITS
    Portable
    0.43
     Portable
    0.42
    portable
    0.40
     নিচ্ছে
    0.40
     ড্র
    0.39
     desapar
    0.39
    adhi
    0.38
     deti
    0.37
    abor
    0.37
    淚
    0.37
    Activations Density 0.000%

    No Known Activations