© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137291
    Prev
    Next
    INDEX
    Explanations

    Old Believer, Old Town, Old East Slavic

    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_12_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
    ii
    0.63
    lj
    0.63
    uer
    0.62
     licenci
    0.58
    ;
    0.57
    lie
    0.55
    nia
    0.55
     Former
    0.54
    );
    0.52
    ix
    0.52
    POSITIVE LOGITS
    ጀም
    0.66
    ハ
    0.61
    ುವ
    0.60
    ای
    0.59
    この
    0.58
    До
    0.58
    على
    0.58
    οντας
    0.57
    ўным
    0.57
    ುತ್ತಿರುವ
    0.57
    Activations Density 0.000%

    No Known Activations