© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11655
    Prev
    Next
    INDEX
    Explanations

    Romance languages, especially Spanish and French

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act · gemini-2.0-flash

    French/Spanish

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Monfieur
    -2.52
     purpoſe
    -2.25
     Diſ
    -2.25
     Reſ
    -2.17
     Majefty
    -2.14
     pleaſure
    -2.13
     Anſ
    -2.11
     houſe
    -2.09
     myſelf
    -2.09
     Theſe
    -2.08
    POSITIVE LOGITS
     Réponses
    1.30
    帖最后由
    1.27
     Qu
    1.27
     Par
    1.27
     Pa
    1.23
     Lu
    1.23
     Ter
    1.23
     Tra
    1.18
     Sa
    1.18
     Me
    1.17
    Activations Density 1.978%

    No Known Activations