Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165750
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    pecific
    0.57
    actionBarTab
    0.52
    邉
    0.52
    etrically
    0.51
    nBitCount
    0.51
    ystem
    0.49
     الوحده
    0.49
    äns
    0.49
    ahan
    0.48
    äg
    0.48
    POSITIVE LOGITS
     Love
    0.45
     [](
    0.44
    Em
    0.44
     Tyl
    0.44
     Seal
    0.44
     Alkal
    0.43
    墙
    0.43
     Scop
    0.43
    Scop
    0.43
     Enable
    0.42
    Activations Density 0.000%

    No Known Activations