© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196322
    Prev
    Next
    INDEX
    Explanations

    central + geographical region

    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_9_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
     certaines
    0.77
    -
    0.71
    ү
    0.68
    어
    0.68
     douloureuse
    0.66
    ী
    0.65
    ми
    0.65
    বিদ
    0.64
     nouvelle
    0.64
    公司
    0.63
    POSITIVE LOGITS
    et
    1.04
    ad
    0.96
    p
    0.94
    il
    0.92
    v
    0.91
    q
    0.88
    ol
    0.82
    r
    0.82
    c
    0.82
    o
    0.79
    Activations Density 0.001%

    No Known Activations