© 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. 10443
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names, location, and organizations

    oai_token-act-pair · 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
    AndEndTag
    -0.57
    ellschaft
    -0.50
     AttributeSet
    -0.47
    Tracce
    -0.47
    Atoi
    -0.46
     insuffisamment
    -0.44
    AttributeSet
    -0.44
    BRA
    -0.44
    rrggbb
    -0.44
    CloseOperation
    -0.44
    POSITIVE LOGITS
     فريبيس
    0.75
    loem
    0.63
     وتسجيلات
    0.62
    +#+
    0.60
     Вікі
    0.60
     ModelExpression
    0.59
    ]]:
    0.58
    webElementXpaths
    0.56
    ']);
    0.56
    %]
    0.56
    Activations Density 2.081%

    No Known Activations