© 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. 1003
    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
     sludge
    1.66
     পরবর্তীতে
    1.47
    Ｋ
    1.45
     lauded
    1.43
     criado
    1.41
    ент
    1.41
     annoyance
    1.40
     خلص
    1.37
    AutoScaleMode
    1.37
     fucked
    1.37
    POSITIVE LOGITS
     thaliana
    1.62
     muut
    1.61
    ,\
    1.55
    se
    1.54
    ž
    1.53
    ala
    1.47
    hua
    1.47
    ti
    1.46
    וה
    1.44
    お得
    1.44
    Activations Density 0.294%

    No Known Activations