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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1205
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ब्ल्यू
    0.83
    ς
    0.79
    ை
    0.77
     withstand
    0.74
    ్ఞ
    0.73
    десят
    0.73
    ын
    0.73
     nought
    0.72
     endowed
    0.68
    ровать
    0.68
    POSITIVE LOGITS
    ️
    0.70
    こちらは
    0.62
     sitio
    0.62
    вно
    0.61
    적인
    0.60
    ate
    0.60
    击
    0.57
     cercano
    0.57
    ed
    0.56
    তম
    0.55
    Activations Density 0.005%

    No Known Activations