© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104574
    Prev
    Next
    INDEX
    Explanations

    Slavic and foreign language origins

    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_1_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
    ات
    1.16
    of
    1.07
     slew
    0.90
    स
    0.90
    ively
    0.89
    پ
    0.89
    ล
    0.87
    G
    0.84
    ले
    0.84
    는데
    0.83
    POSITIVE LOGITS
     extranj
    1.27
    ن
    1.16
    SXml
    1.14
    밂
    1.13
    نې
    1.07
    n
    1.05
    ncia
    1.05
    ナ
    1.03
    νει
    1.02
    ScriptBuf
    1.02
    Activations Density 0.000%

    No Known Activations