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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32208
    Prev
    Next
    INDEX
    Explanations

    states or indicates limitations

    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_31_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
    ❂
    0.32
     AE
    0.31
    try
    0.31
    AE
    0.30
     لاع
    0.30
     Cots
    0.30
    প্রিয়
    0.30
    _\
    0.30
    gri
    0.29
     Leisure
    0.29
    POSITIVE LOGITS
     фаразлау
    0.39
     положения
    0.39
     polig
    0.39
     capacidades
    0.38
     ਅਤੇ
    0.37
     डिटेल्स
    0.37
     штра
    0.37
     baseY
    0.36
     récomp
    0.36
     multiplier
    0.36
    Activations Density 0.004%

    No Known Activations