© 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. 11514
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of people or places.

    oai_token-act-pair · gemini-2.0-flash

    Italian context

    np_max-act-logits · 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
    })*/
    -0.52
     Wikispecies
    -0.50
    KommentareTeilen
    -0.47
    cloudfront
    -0.46
    kubernetes
    -0.45
     inoxidable
    -0.45
     catalana
    -0.45
    WEBPACK
    -0.44
     שוליים
    -0.44
     proceeds
    -0.44
    POSITIVE LOGITS
    CloseOperation
    0.61
    RegressionTest
    0.56
    %)$
    0.54
    ándola
    0.54
     endforeach
    0.53
    новниш
    0.53
    adaptiveStyles
    0.52
     engraçadas
    0.52
    pired
    0.50
    PreferredItem
    0.49
    Activations Density 0.416%

    No Known Activations