© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14003
    Prev
    Next
    INDEX
    Explanations

    terms and reactions related to chemistry and scientific studies

    oai_token-act-pair · gemini-2.0-flash

    words or tokens beginning with 'ald' or 'skri'

    np_token-act-pair-logits · gpt-4o-mini

    Chemical reactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     pleaſure
    -0.67
     Reſ
    -0.59
     purpoſe
    -0.58
    LookAnd
    -0.57
     diſt
    -0.57
    DockStyle
    -0.56
    contentLoaded
    -0.55
     Shakspeare
    -0.55
    neux
    -0.54
     समीक्षाओं
    -0.54
    POSITIVE LOGITS
     ald
    0.50
     topp
    0.49
     skri
    0.48
     self
    0.47
    Stad
    0.47
    elen
    0.47
    aldas
    0.47
    FontSize
    0.47
    XmlAccessType
    0.46
     кӀ
    0.45
    Activations Density 2.539%

    No Known Activations