© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121841
    Prev
    Next
    INDEX
    Explanations

    Asian Games, country, nation, Royale

    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_3_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
    ו
    0.75
    I
    0.68
    و
    0.66
    asını
    0.60
    ં
    0.58
    na
    0.55
    unde
    0.55
    ளம்
    0.54
    ą
    0.54
    ⠑
    0.54
    POSITIVE LOGITS
    =\
    0.77
    تم
    0.70
    اک
    0.66
    ک
    0.64
    اح
    0.63
    یت
    0.63
    الح
    0.63
    \}\
    0.63
    سی
    0.62
    㗽
    0.61
    Activations Density 0.000%

    No Known Activations