© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13919
    Prev
    Next
    INDEX
    Explanations

    political bias and negative sentiment, especially when discussing politicians

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     open
    -0.57
    Open
    -0.52
     Open
    -0.48
    "}>
    -0.47
    \",\
    -0.47
    ERTS
    -0.47
     execução
    -0.46
    ThemeOverlay
    -0.46
    open
    -0.45
    '));
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.79
     snippetHide
    0.73
    تقاوى
    0.68
    
    0.63
    InputBorder
    0.61
    PhysRevD
    0.61
     незавершена
    0.60
     lying
    0.60
    ChildScrollView
    0.60
    TagMode
    0.59
    Activations Density 2.342%

    No Known Activations