© 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. 9407
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Bristol, especially in connection with Southmead Hospital

    oai_token-act-pair · gemini-2.0-flash

    Bristol

    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
     on
    -0.56
     onto
    -0.52
     onboard
    -0.52
     сожалению
    -0.47
    ulturen
    -0.45
    Ufficio
    -0.44
     ErrIntOverflow
    -0.42
     passare
    -0.42
    bodyParser
    -0.42
    omen
    -0.42
    POSITIVE LOGITS
    aarrggbb
    0.88
     disambiguazione
    0.82
    RenderAtEndOf
    0.78
    verwijspagina
    0.75
     estekak
    0.74
    StoryboardSegue
    0.73
    awtextra
    0.72
    ValueStyle
    0.66
    LOAT
    0.65
    oredCriteria
    0.62
    Activations Density 0.605%

    No Known Activations