© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61771
    Prev
    Next
    INDEX
    Explanations

    sakrifizioa, sakonean, lehen

    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
    த
    1.05
     The
    1.02
     sadrž
    0.99
    šću
    0.96
     somet
    0.92
     scrutin
    0.92
    زمانہ
    0.92
    ка
    0.91
    ING
    0.91
     grados
    0.89
    POSITIVE LOGITS
    س
    1.14
    st
    1.13
    ز
    1.11
    с
    1.07
    در
    1.02
    et
    1.00
    स
    0.97
    ry
    0.95
    embangan
    0.95
    いた
    0.94
    Activations Density 0.000%

    No Known Activations