© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9138
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to personal opinions, reactions, and potential future outcomes.

    oai_token-act-pair · gemini-2.0-flash

    viewpoints

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     InputDecoration
    -0.76
    RegistryLite
    -0.71
     متعلقه
    -0.66
    SequentialGroup
    -0.63
     ModelExpression
    -0.63
    basicConfig
    -0.63
    =$?
    -0.59
     Universitaria
    -0.56
     Woodruff
    -0.56
    complexContent
    -0.54
    POSITIVE LOGITS
     view
    1.35
     attitude
    1.23
     views
    1.18
     approach
    1.16
    attitude
    1.10
     attitudes
    1.09
     View
    1.09
    view
    1.09
    approach
    1.08
     Views
    1.03
    Activations Density 1.183%

    No Known Activations