© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194511
    Prev
    Next
    INDEX
    Explanations

    place 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_15_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
     earthqu
    0.50
     adhipp
    0.47
     ″
    0.46
    驒
    0.44
     c
    0.44
     Tallinn
    0.44
     cim
    0.43
     кул
    0.43
     мелдеш
    0.42
     dukkham
    0.42
    POSITIVE LOGITS
    ir
    0.46
    ATE
    0.41
    adhy
    0.41
    is
    0.41
    HO
    0.40
    会
    0.40
    TE
    0.39
    会的
    0.39
     needs
    0.38
    可以
    0.38
    Activations Density 0.031%

    No Known Activations