© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7146
    Prev
    Next
    INDEX
    Explanations

    fragments of code where strings are being concatenated

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks

    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
    Negative Logits
    amilya
    -0.53
     Viana
    -0.53
    HasAnnotation
    -0.52
     Clube
    -0.52
     eels
    -0.51
     Notícias
    -0.51
     aéreo
    -0.50
     féminin
    -0.50
     vlas
    -0.49
     Formación
    -0.49
    POSITIVE LOGITS
     مشين
    1.00
    +#+#
    0.85
    addCriterion
    0.75
     विश्वसनीयता
    0.71
     '\\;'
    0.67
    MetaObject
    0.66
    دانشنامهٔ
    0.65
    parsedMessage
    0.65
    queryInterface
    0.64
    Hochspringen
    0.63
    Activations Density 0.764%

    No Known Activations