© 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. 1554
    Prev
    Next
    INDEX
    Explanations

    words that might identify law or news articles

    oai_token-act-pair · 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
    asgi
    -0.57
     ro
    -0.47
     ne
    -0.46
    ynen
    -0.46
    licula
    -0.46
    >');
    -0.45
     such
    -0.45
     <
    -0.45
    testcase
    -0.45
     ve
    -0.44
    POSITIVE LOGITS
     itſelf
    0.96
     pleaſure
    0.93
     themſelves
    0.90
     myſelf
    0.85
     greateſt
    0.84
     Theſe
    0.82
     purpoſe
    0.80
     Walkover
    0.79
     becauſe
    0.78
     Reſ
    0.78
    Activations Density 3.056%

    No Known Activations