© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59308
    Prev
    Next
    INDEX
    Explanations

    going to, going on, going through

    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_11_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
    ja
    0.62
    et
    0.62
    sa
    0.60
    因为它
    0.60
    z
    0.59
    Name
    0.58
    Na
    0.58
    y
    0.58
    8
    0.57
    apu
    0.57
    POSITIVE LOGITS
     vivos
    0.61
     האט
    0.57
     رضی
    0.56
     গেছেন
    0.56
     nipples
    0.55
     timelines
    0.54
     ceases
    0.54
     انھیں
    0.54
    베이스
    0.53
     cease
    0.52
    Activations Density 0.000%

    No Known Activations