© 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. 4200
    Prev
    Next
    INDEX
    Explanations

    technical documents and religious and medical jargon

    oai_token-act-pair · gemini-2.0-flash

    sheet

    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
    <bos>
    -0.59
     when
    -0.56
     if
    -0.54
     with
    -0.52
     for
    -0.52
     is
    -0.52
     that
    -0.52
    ？　
    -0.52
     because
    -0.52
     we
    -0.51
    POSITIVE LOGITS
     تانيه
    0.72
     kasarigan
    0.71
    BibitemShut
    0.69
    Jeografia
    0.66
    Externé
    0.66
    "';
    0.63
    </code>
    0.63
     Efq
    0.61
    ]")]
    0.60
    PreferredItem
    0.59
    Activations Density 4.350%

    No Known Activations