© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212446
    Prev
    Next
    INDEX
    Explanations

    joined-up services

    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_5_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
    이었
    1.33
    은
    1.22
    ка
    1.21
    ון
    1.11
    리고
    1.10
     dangereux
    1.08
    が
    1.08
    이지만
    1.07
    {//
    1.06
    ですが
    1.05
    POSITIVE LOGITS
    il
    1.39
    n
    1.37
    .
    1.30
     for
    1.25
    ys
    1.22
    ao
    1.20
     it
    1.19
     the
    1.18
    z
    1.17
    ind
    1.16
    Activations Density 0.000%

    No Known Activations