© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12186
    Prev
    Next
    INDEX
    Explanations

    references to the word "Federal", with increased activation if "Federal" is followed by a capitalized word.

    oai_token-act-pair · gemini-2.0-flash

    Federal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    tagHelperRunner
    -0.76
     Fa
    -0.71
     Fur
    -0.67
     Fel
    -0.63
     Fo
    -0.62
     Flu
    -0.62
     Fen
    -0.61
     Fl
    -0.61
     Fis
    -0.61
     Fog
    -0.59
    POSITIVE LOGITS
    f
    1.02
     f
    0.87
    fml
    0.74
    𝐟
    0.74
    참고
    0.70
     fVar
    0.70
     fii
    0.70
    𝗳
    0.69
    fi
    0.69
    fff
    0.69
    Activations Density 1.911%

    No Known Activations