© 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. 59624
    Prev
    Next
    INDEX
    Explanations

    limitation, limited, beschränkter

    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
    i
    0.68
    cmap
    0.64
    。
    0.60
    dine
    0.57
    cron
    0.57
    about
    0.56
    c
    0.56
    im
    0.55
    cry
    0.54
    city
    0.54
    POSITIVE LOGITS
     Frege
    0.59
    芗
    0.59
     War
    0.59
     Rutgers
    0.58
     Georgetown
    0.58
     Avant
    0.58
     artística
    0.57
     Rar
    0.56
    薇
    0.56
     Sony
    0.55
    Activations Density 0.001%

    No Known Activations