© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13134
    Prev
    Next
    INDEX
    Explanations

    words that have a slightly positive or slightly negative connotation that are often used in research papers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     wireType
    -0.83
    Παραπομπές
    -0.82
     oxidase
    -0.76
    Искәрмәләр
    -0.76
     חיצוניים
    -0.75
     quoque
    -0.71
    skosten
    -0.69
    ﹉
    -0.69
    ніципа
    -0.66
     Clocks
    -0.66
    POSITIVE LOGITS
    #+#
    0.69
    queryInterface
    0.54
    .`
    0.49
    the
    0.45
    TagMode
    0.44
     nå
    0.41
    *
    0.40
     rằng
    0.40
     nyt
    0.38
    ///</
    0.38
    Activations Density 9.395%

    No Known Activations