© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56768
    Prev
    Next
    INDEX
    Explanations

    Antarctic peninsula continent treaty system

    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_11_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
     oors
    0.20
     terbatas
    0.19
     سسٹم
    0.18
     basa
    0.18
     berlang
    0.18
     beteg
    0.18
     க
    0.18
     аса
    0.18
    μένη
    0.18
    డుగు
    0.18
    POSITIVE LOGITS
    id
    0.25
    RECT
    0.22
    %
    0.21
    RH
    0.21
    E
    0.21
    INK
    0.21
    e
    0.20
    END
    0.20
    NH
    0.20
    vand
    0.20
    Activations Density 0.003%

    No Known Activations