© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11131
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to praise, awards, elections, campaigns, gender, or job applications

    oai_token-act-pair · gemini-2.0-flash

    public notice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    EndInit
    -0.58
     localObject
    -0.57
     radioactivity
    -0.50
     setuptools
    -0.50
    ngiliz
    -0.49
    offsetWidth
    -0.48
     paparazzi
    -0.47
    ładka
    -0.46
    prefixer
    -0.46
    Mani
    -0.46
    POSITIVE LOGITS
    fjspx
    0.64
    zoon
    0.56
    +:+
    0.56
     Himo
    0.55
    ErrUnexpectedEOF
    0.53
    contentLoaded
    0.50
     ویکی‌پدی
    0.50
    herself
    0.50
    reportError
    0.49
     onView
    0.49
    Activations Density 34.995%

    No Known Activations