© 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. 13794
    Prev
    Next
    INDEX
    Explanations

    military bases and installations

    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
     Гра
    0.57
     Г
    0.55
    }^{+}$
    0.55
     Indexes
    0.55
     μουσ
    0.55
     Netherlands
    0.54
    ernsey
    0.54
     酸
    0.54
    воря
    0.54
     Providers
    0.54
    POSITIVE LOGITS
    此
    0.52
    ണ്ഡി
    0.51
    AC
    0.50
    헤
    0.50
     fes
    0.49
    賚
    0.49
    jekte
    0.49
    牠
    0.49
    驥
    0.49
     biceps
    0.47
    Activations Density 0.011%

    No Known Activations