© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14549
    Prev
    Next
    INDEX
    Explanations

    place names with prepositions

    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_13_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
     marks
    0.57
     impetus
    0.57
     =
    0.54
     lifestyles
    0.54
    imist
    0.53
    tors
    0.51
     says
    0.51
    EN
    0.50
    ifold
    0.50
    xit
    0.50
    POSITIVE LOGITS
     slew
    0.59
    тера
    0.58
     pInBuffer
    0.55
    롭게
    0.55
     אשר
    0.53
    த்தொ
    0.52
    //}
    0.51
    ujukan
    0.51
    系列的
    0.50
     によって
    0.50
    Activations Density 0.001%

    No Known Activations