© 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. 8323
    Prev
    Next
    INDEX
    Explanations

    words ending in "ly" and "y", parenthetical phrases, and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    respectively

    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
    $/,
    -0.54
    oredCriteria
    -0.52
    cited
    -0.52
    們
    -0.50
    )];
    -0.50
    ธ์
    -0.50
    urable
    -0.49
    '],
    -0.49
    `,
    -0.49
    "])
    -0.49
    POSITIVE LOGITS
    GraphicsUnit
    0.57
    .
    0.56
    ercito
    0.52
     mariée
    0.51
    ffilm
    0.51
    setContentView
    0.49
    SpringRunner
    0.49
    ----</
    0.49
     publicação
    0.48
    jestel
    0.48
    Activations Density 15.895%

    No Known Activations