© 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. 15043
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conditional clauses and prepositions.

    oai_token-act-pair · gemini-2.0-flash

    determiners

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

    indefinite article

    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
    jooq
    -0.75
    XmlAccessorType
    -0.70
    Personendaten
    -0.69
     nahilalakip
    -0.69
    featureID
    -0.68
    scryfall
    -0.67
    олові
    -0.64
    ArrowToggle
    -0.63
    UserScript
    -0.63
    EndGlobalSection
    -0.63
    POSITIVE LOGITS
     a
    1.45
     an
    1.25
     another
    0.79
     sebuah
    0.79
     eine
    0.75
     einem
    0.71
     einen
    0.70
     einer
    0.69
     seorang
    0.69
     eenen
    0.68
    Activations Density 8.724%

    No Known Activations