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

    Neuronpedia

    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. 971
    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
    esque
    0.79
     prostaglandins
    0.75
    ⺈
    0.70
    т
    0.68
    ٠
    0.65
     độ
    0.63
    csak
    0.62
    MAPE
    0.61
    ATORY
    0.61
     zwar
    0.61
    POSITIVE LOGITS
    ことを
    0.66
    StringType
    0.64
    ਰੀ
    0.64
     corporal
    0.63
     reputed
    0.63
     químicos
    0.62
    modifier
    0.61
    ся
    0.60
    臾
    0.59
    습니다
    0.59
    Activations Density 0.042%

    No Known Activations