© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 204404
    Prev
    Next
    INDEX
    Explanations

    delays

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    通
    0.38
    ัฐ
    0.38
     aliqua
    0.36
     riguardo
    0.36
    äche
    0.36
    stasy
    0.36
     അധിക
    0.36
    दछ
    0.36
     тала
    0.36
     ус
    0.35
    POSITIVE LOGITS
     impacts
    0.45
     build
    0.45
     impact
    0.44
     times
    0.44
     IMPACT
    0.39
    ..<
    0.39
     accessing
    0.38
     segment
    0.37
     Impact
    0.37
     implementing
    0.36
    Activations Density 0.003%

    No Known Activations