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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196946
    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_26_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
     vandal
    0.50
    ការពារ
    0.49
     Pioneers
    0.49
     countably
    0.46
    俘
    0.46
     ambientale
    0.46
     Commander
    0.46
     prevención
    0.45
     pozdě
    0.45
     schafft
    0.45
    POSITIVE LOGITS
    ر
    0.65
    (\
    0.48
    ising
    0.48
    ר
    0.47
    ის
    0.47
    )\,
    0.47
    ingo
    0.46
    olysis
    0.46
    agamanam
    0.45
    arded
    0.45
    Activations Density 0.000%

    No Known Activations