© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15234
    Prev
    Next
    INDEX
    Explanations

    mentions of figures and captions in scientific documents and code

    oai_token-act-pair · gemini-2.0-flash

    caption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    SocketChannel
    -0.53
     vPvB
    -0.52
     }}">
    -0.52
    JdbcTemplate
    -0.50
    binaan
    -0.50
     joaat
    -0.50
    tserrat
    -0.49
     BoxDecoration
    -0.49
    %;
    -0.48
    softc
    -0.48
    POSITIVE LOGITS
    jsonwebtoken
    0.66
     Captions
    0.64
     caption
    0.63
    GOTREF
    0.60
     captions
    0.59
     Caption
    0.59
    <bos>
    0.57
    LBL
    0.57
    caption
    0.56
    parsedMessage
    0.54
    Activations Density 3.548%

    No Known Activations