© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104539
    Prev
    Next
    INDEX
    Explanations

    Somaliland, Som, Tajikistan, Bag, Mi respond

    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_1_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
     on
    1.03
    <
    0.99
    産の
    0.90
     recomend
    0.88
    LY
    0.88
     murmur
    0.87
    ολ
    0.87
     alimentare
    0.86
    (
    0.85
    VER
    0.84
    POSITIVE LOGITS
    at
    1.44
    is
    1.35
    et
    1.30
    it
    1.27
    k
    1.23
    ي
    1.22
    ك
    1.22
    ด์
    1.17
    та
    1.14
    re
    1.12
    Activations Density 0.000%

    No Known Activations