© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16376
    Prev
    Next
    INDEX
    Explanations

    French language

    oai_token-act-pair · gemini-2.0-flash

    French articles

    np_max-act-logits · gemini-2.0-flash

    French articles

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unknow
    -0.51
     bromine
    -0.50
     Jodie
    -0.49
     fates
    -0.48
    irmingham
    -0.48
     eof
    -0.48
    (++
    -0.47
    ihr
    -0.47
     coleção
    -0.47
     Jurí
    -0.47
    POSITIVE LOGITS
    发表于
    0.53
    脚注の使い方
    0.52
     &___
    0.50
     nakalista
    0.48
     ModelExpression
    0.48
     سكانية
    0.48
    Välislingid
    0.47
    httphttps
    0.46
     विश्वसनीयता
    0.45
    __':
    0.44
    Activations Density 0.357%

    No Known Activations