© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13770
    Prev
    Next
    INDEX
    Explanations

    sentences about recommendations or considerations

    oai_token-act-pair · gemini-2.0-flash

    instances of the word 'when' in various languages

    np_token-act-pair-logits · gpt-4o-mini

    considering different factors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    قایناقلار
    -0.54
    ьаж
    -0.52
    ագրություններ
    -0.50
    ModelAdmin
    -0.50
    ونز
    -0.49
    )‏
    -0.49
    Lähteet
    -0.49
    oredCriteria
    -0.49
    äss
    -0.48
    ただ
    -0.47
    POSITIVE LOGITS
     when
    2.55
    when
    2.23
     quando
    2.00
     cuando
    1.95
     когда
    1.79
    When
    1.79
     When
    1.72
     WHEN
    1.72
    cuando
    1.66
     lorsque
    1.57
    Activations Density 6.817%

    No Known Activations