© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134330
    Prev
    Next
    INDEX
    Explanations

    village/city names

    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_6_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
     څنګه
    1.26
    其他
    1.18
    נ
    1.14
    يا
    1.12
    Са
    1.06
    са
    1.05
    ма
    1.02
    Kako
    1.02
    בא
    1.01
     giocatore
    1.00
    POSITIVE LOGITS
    ,
    1.35
    س
    1.16
    /
    1.09
     (
    1.03
    ik
    1.01
    v
    1.00
    ate
    0.97
     $
    0.92
    ون
    0.92
    ral
    0.90
    Activations Density 0.000%

    No Known Activations