© 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. 854
    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
    ר
    2.88
    ن
    2.80
    र
    2.66
    نك
    2.55
    n
    2.21
    𝘦
    2.17
    ీ
    2.13
     इससे
    2.13
    nement
    2.09
     invention
    2.08
    POSITIVE LOGITS
    ant
    2.16
    ї
    1.83
    стите
    1.83
    नेटरी
    1.69
    И
    1.65
     méridionale
    1.62
     таки
    1.62
     स्थलों
    1.62
    었
    1.62
    𝗘
    1.58
    Activations Density 0.007%

    No Known Activations