© 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. 9430
    Prev
    Next
    INDEX
    Explanations

    instances of personal interaction, especially between people and them

    oai_token-act-pair · gemini-2.0-flash

    keywords related to digital content creation

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

    CreateModel

    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
    $'
    -0.82
    expandindo
    -0.72
     ویکی‌پدیای
    -0.68
    ]'
    -0.67
    }'
    -0.67
    '],$
    -0.66
    their
    -0.65
    \""
    -0.63
     their
    -0.63
    `
    -0.62
    POSITIVE LOGITS
    CreateModel
    0.56
    +:+
    0.52
    .
    0.48
     hombro
    0.47
    IMPORTED
    0.47
     cappello
    0.46
    ksesta
    0.46
     cipolla
    0.46
    허
    0.46
    EClass
    0.45
    Activations Density 17.167%

    No Known Activations