© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13512
    Prev
    Next
    INDEX
    Explanations

    scientific papers

    oai_token-act-pair · gemini-2.0-flash

    reporting verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     CrossRef
    -0.51
    цездатний
    -0.49
    posia
    -0.47
    abbé
    -0.45
     Referential
    -0.45
    참고
    -0.44
    ække
    -0.43
     CURIAM
    -0.43
    genstein
    -0.43
    ่านั้น
    -0.42
    POSITIVE LOGITS
    RepeatedField
    0.70
    .*")]
    0.63
    ंदीखरीदारी
    0.62
    ême
    0.60
     nakalista
    0.60
    tagHelperRunner
    0.59
    AutoScale
    0.58
    Begriffsklä
    0.56
    inerary
    0.56
    GEBURTSDATUM
    0.56
    Activations Density 44.078%

    No Known Activations