© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81853
    Prev
    Next
    INDEX
    Explanations

    geechee, lychee, fēn

    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_0_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
     for
    1.87
    1
    1.59
     with
    1.30
     I
    1.29
    siniz
    1.24
     (
    1.17
     from
    1.14
    '>
    1.12
    src
    1.11
     \
    1.07
    POSITIVE LOGITS
    ä
    1.91
    og
    1.72
    ב
    1.55
    ุ
    1.51
    ash
    1.49
    ow
    1.48
    ین
    1.47
    ast
    1.44
    ub
    1.39
    .
    1.33
    Activations Density 0.000%

    No Known Activations