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. 165796
    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
    п
    0.49
     Departments
    0.48
     refining
    0.47
     Examples
    0.47
     indecent
    0.47
    r
    0.47
     intestine
    0.46
     Department
    0.45
    ،
    0.45
     ref
    0.44
    POSITIVE LOGITS
     पै
    0.50
    Madrid
    0.49
    Miguel
    0.48
    María
    0.48
    Sight
    0.47
    Hyderabad
    0.47
     algunas
    0.47
    fik
    0.47
    Pedido
    0.46
    Naj
    0.46
    Activations Density 0.000%

    No Known Activations