© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44146
    Prev
    Next
    INDEX
    Explanations

    notification and email alerts

    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
    ｒ
    0.57
     windings
    0.55
     manoeuvre
    0.54
     manoeuv
    0.54
     amid
    0.53
     welds
    0.53
    ogra
    0.52
     stirs
    0.52
    ation
    0.52
    entarios
    0.52
    POSITIVE LOGITS
    Downtown
    0.62
    م
    0.61
    凌晨
    0.58
    ت
    0.57
    ب
    0.55
    Archer
    0.55
    Middle
    0.54
    Privacy
    0.53
    中
    0.53
    Little
    0.53
    Activations Density 0.053%

    No Known Activations