© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217533
    Prev
    Next
    INDEX
    Explanations

    place names followed by state or country

    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_31_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
    don
    0.36
     रीजनिंग
    0.35
     ಜೋ
    0.34
    spirited
    0.34
    ástico
    0.33
    showerror
    0.33
    魃
    0.33
    <unused400>
    0.33
     Großbritannien
    0.33
    StarService
    0.32
    POSITIVE LOGITS
     bony
    0.31
     leg
    0.31
     caf
    0.30
     –
    0.29
     hostname
    0.29
     lady
    0.29
     moyen
    0.29
     II
    0.29
     inlets
    0.29
     cer
    0.29
    Activations Density 0.000%

    No Known Activations