© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13273
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that indicate relationships or qualifiers within an idea or argument.

    oai_token-act-pair · gemini-2.0-flash

    Possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    selves
    -0.84
     Reverso
    -0.73
    เอง
    -0.66
    esterday
    -0.64
     Vikipedi
    -0.61
    曖昧さ回避
    -0.61
    NUMX
    -0.61
    herself
    -0.61
     مشين
    -0.61
    éphane
    -0.61
    POSITIVE LOGITS
     your
    1.66
     our
    1.49
     his
    1.42
     my
    1.38
     their
    1.34
    your
    1.20
     seu
    1.18
     sua
    1.13
     seus
    1.05
    our
    1.05
    Activations Density 4.551%

    No Known Activations