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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 261470
    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_5_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
    ो
    0.91
    dı
    0.83
    و
    0.78
     불구하고
    0.72
    ce
    0.68
    credit
    0.67
    ede
    0.65
    h
    0.64
    ”
    0.64
    chlor
    0.62
    POSITIVE LOGITS
     Lleg
    0.72
    తో
    0.71
     término
    0.70
    يات
    0.68
     clasific
    0.66
    AH
    0.66
    s
    0.66
    দের
    0.65
    ση
    0.64
     Ajust
    0.63
    Activations Density 0.000%

    No Known Activations