© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7691
    Prev
    Next
    INDEX
    Explanations

    words for elements or chemical compounds, especially ones ending in "-ane", "-ol", "-ide", or "-ium" and also references to molar concentrations or percentages.

    oai_token-act-pair · gemini-2.0-flash

    chemistry contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AddTagHelper
    -0.92
    RectangleBorder
    -0.84
    ngdoc
    -0.79
    NameInMap
    -0.78
     CreateTagHelper
    -0.78
     AssemblyCulture
    -0.77
    CURLOPT
    -0.73
    parsedMessage
    -0.72
    ecma
    -0.71
    ApplicationTests
    -0.69
    POSITIVE LOGITS
     préférence
    0.49
    plona
    0.43
     espagne
    0.42
     Ahnung
    0.41
     Norvège
    0.41
     pesados
    0.41
     assoluto
    0.40
    íncipe
    0.40
     cerrados
    0.40
     gesloten
    0.40
    Activations Density 1.955%

    No Known Activations