© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109711
    Prev
    Next
    INDEX
    Explanations

    tribal warfare and populations

    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_2_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
     is
    1.02
    ia
    0.96
    ;
    0.96
    ete
    0.95
    ick
    0.91
     miserable
    0.89
    い
    0.89
     figurative
    0.87
     budding
    0.83
     undecided
    0.81
    POSITIVE LOGITS
    t
    1.37
    s
    1.36
    for
    1.25
    from
    1.13
    al
    1.10
    ليه
    1.09
    et
    1.04
    لها
    1.04
    3
    1.04
    。
    1.03
    Activations Density 0.000%

    No Known Activations