© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87265
    Prev
    Next
    INDEX
    Explanations

    events held in schools

    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_23_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
    indeterminate
    0.29
    acios
    0.27
    engineering
    0.27
     inseparable
    0.27
     sadly
    0.26
    ú
    0.26
     marriage
    0.26
    𝙴
    0.26
     monarchs
    0.26
     landlord
    0.25
    POSITIVE LOGITS
     BERT
    0.29
    Viol
    0.27
     висо
    0.27
     свето
    0.27
    DST
    0.27
     Yesterday
    0.27
     ступен
    0.27
     பட்ட
    0.26
     μην
    0.26
     если
    0.26
    Activations Density 0.000%

    No Known Activations