© 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. 59312
    Prev
    Next
    INDEX
    Explanations

    graceful exit

    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
    点
    0.66
    ق
    0.65
     Dünya
    0.53
     Tolerance
    0.53
     Comunidad
    0.52
     Republike
    0.52
     ČR
    0.52
    発売
    0.51
    身
    0.50
    無論
    0.50
    POSITIVE LOGITS
     awakened
    0.64
     grandes
    0.64
     haird
    0.63
     overheat
    0.63
     advertisements
    0.62
     goat
    0.62
     adventures
    0.62
    j
    0.61
    t
    0.60
     chicks
    0.59
    Activations Density 0.003%

    No Known Activations