© 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. 7915
    Prev
    Next
    INDEX
    Explanations

    words related to data analysis and feature selection for machine learning

    oai_token-act-pair · gemini-2.0-flash

    mathematical or statistical symbols and terms

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

    Feature selection

    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
    osoba
    -0.74
     EconPapers
    -0.69
     nakalista
    -0.64
    KommentareTeilen
    -0.60
    出版年
    -0.58
    Personensuche
    -0.58
     مشين
    -0.57
    UnknownFieldSet
    -0.55
     ModelExpression
    -0.54
    oa̍t
    -0.54
    POSITIVE LOGITS
    җ
    0.56
    τζ
    0.51
    __*/
    0.50
    ṁ
    0.49
    resenta
    0.47
     ($(
    0.46
     Wur
    0.46
    Crédit
    0.46
     Bell
    0.44
     Zimmermann
    0.44
    Activations Density 15.950%

    No Known Activations