© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15085
    Prev
    Next
    INDEX
    Explanations

    terms related to US politics and corporations, in a negative light.

    oai_token-act-pair · gemini-2.0-flash

    business and corporations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    UnusedPrivate
    -0.80
    WebElementEntity
    -0.80
    AndEndTag
    -0.75
    QMetaType
    -0.74
    makeConstraints
    -0.74
     виправивши
    -0.71
    MessageTagHelper
    -0.69
     <=",
    -0.68
    ArrowToggle
    -0.68
    ConstraintMaker
    -0.65
    POSITIVE LOGITS
    ługo
    0.50
     solas
    0.49
     solidarité
    0.48
     approche
    0.47
     attentes
    0.46
     licha
    0.46
     éti
    0.45
     rechange
    0.45
     positifs
    0.44
     normaux
    0.44
    Activations Density 2.261%

    No Known Activations