© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163576
    Prev
    Next
    INDEX
    Explanations

    `test_` prefixes

    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_13_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
    кала
    0.25
    ávají
    0.24
    )"
    0.24
    햐
    0.24
    damian
    0.24
    Ле
    0.23
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.23
    Д
    0.23
    къ
    0.22
    populations
    0.22
    POSITIVE LOGITS
     python
    0.24
     if
    0.23
     college
    0.23
     desarroll
    0.22
     nurse
    0.21
     frio
    0.21
    ᅧ
    0.21
     index
    0.21
     program
    0.21
     extensão
    0.21
    Activations Density 0.002%

    No Known Activations