© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205428
    Prev
    Next
    INDEX
    Explanations

    custom code or functions

    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_6_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
    },
    1.27
    ’,
    1.22
    の高い
    1.06
     кожного
    1.02
    ”,
    1.02
    iva
    1.00
     і
    1.00
     },
    0.99
    guna
    0.99
     »,
    0.98
    POSITIVE LOGITS
    د
    1.47
    ين
    1.21
    in
    1.20
    f
    1.16
    م
    1.16
    ム
    1.13
    "
    1.02
    ной
    1.01
    o
    0.95
    اد
    0.94
    Activations Density 0.004%

    No Known Activations