© 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. 9055
    Prev
    Next
    INDEX
    Explanations

    places and geographical regions

    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
    accia
    0.57
     শিক্ষার্থীদের
    0.56
    даги
    0.55
    夶
    0.55
     titular
    0.55
     CGC
    0.54
     नै
    0.54
    থি
    0.54
    cées
    0.54
    کریاں
    0.54
    POSITIVE LOGITS
     Birmingham
    0.56
    Birmingham
    0.51
     Midlands
    0.50
    ଇ
    0.49
     поса
    0.48
    ാലി
    0.48
    Пло
    0.48
     army
    0.47
    ಾಸ
    0.47
     Пло
    0.47
    Activations Density 0.014%

    No Known Activations