© 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. 1694
    Prev
    Next
    INDEX
    Explanations

    the word "comes" which is associated with new software that improves on or replaces old software

    oai_token-act-pair · gemini-2.0-flash

    come

    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
     auffi
    -0.65
    findpost
    -0.61
     VIDEOTAPE
    -0.57
     Shakspeare
    -0.57
     perfons
    -0.56
    ∎
    -0.54
     Simba
    -0.52
    ]));
    -0.51
     ſtate
    -0.50
    bitField
    -0.50
    POSITIVE LOGITS
     come
    1.54
     comes
    1.50
    come
    1.29
    comes
    1.28
     Come
    1.26
     Comes
    1.23
    Come
    1.20
     handy
    1.17
     COME
    1.16
    Comes
    1.13
    Activations Density 0.782%

    No Known Activations