© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12109
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and car technology

    oai_token-act-pair · gemini-2.0-flash

    Technical reports/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Bioaccumulative
    -0.60
     Sched
    -0.59
     Punct
    -0.54
    Abitanti
    -0.53
    ndel
    -0.53
    商品説明
    -0.52
     onCancelled
    -0.52
     Dux
    -0.52
    Дереккөздер
    -0.51
     useCallback
    -0.51
    POSITIVE LOGITS
    enterOuterAlt
    0.60
     חיצוניים
    0.51
    ArrowToggle
    0.50
     о
    0.50
    ведений
    0.49
    SharedDtor
    0.48
    printStackTrace
    0.47
     об
    0.45
    ЖЕ
    0.44
    веде
    0.44
    Activations Density 0.295%

    No Known Activations