© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11919
    Prev
    Next
    INDEX
    Explanations

    first person opinions relating to faith

    oai_token-act-pair · gemini-2.0-flash

    expressing personal opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     ویکی‌پدی
    -0.62
    addCriterion
    -0.53
    orka
    -0.47
    Rüyada
    -0.47
     Bergmann
    -0.47
    Autoritní
    -0.46
     BoxDecoration
    -0.46
     elseif
    -0.46
     Paglinawan
    -0.45
    ()?;
    -0.45
    POSITIVE LOGITS
     }}"
    0.56
    yaszt
    0.54
    featureID
    0.52
    __(/*!
    0.50
    DoubleQuotes
    0.49
    othelioma
    0.48
     مشين
    0.48
    
    0.48
    permitAll
    0.48
    بين
    0.48
    Activations Density 1.681%

    No Known Activations