© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 11069
    Prev
    Next
    INDEX
    Explanations

    references to document and timing, and some positive/negative sentiment

    oai_token-act-pair · gemini-2.0-flash

    doc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     pouvoit
    -1.26
     mauva
    -1.24
     avoient
    -1.23
     >=",
    -1.23
    AsUp
    -1.23
     dieux
    -1.23
     enfans
    -1.19
     prêtres
    -1.19
     kasarigan
    -1.18
     feroit
    -1.18
    POSITIVE LOGITS
    ↵↵
    1.08
     
    0.90
    s
    0.81
    </h2>
    0.79
     "
    0.78
    '
    0.73
    -
    0.69
    <h2>
    0.69
     the
    0.68
    </h3>
    0.66
    Activations Density 1.974%

    No Known Activations