© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7688
    Prev
    Next
    INDEX
    Explanations

    angle brackets that appear to be the start of HTML tags

    oai_token-act-pair · gemini-2.0-flash

    technical terms and file formats

    np_token-act-pair-logits · gpt-4o-mini

    XML-related content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ęż
    -0.48
     IgA
    -0.46
    MessageTagHelper
    -0.45
     musicales
    -0.45
    نج
    -0.44
    jsonp
    -0.44
    Bonjour
    -0.44
     Interne
    -0.44
     def
    -0.43
     Inspectors
    -0.43
    POSITIVE LOGITS
    Personensuche
    0.75
    Hentet
    0.68
    UnusedPrivate
    0.67
    دانشنامهٔ
    0.66
    المشاركات
    0.64
    DeleteBehavior
    0.63
    
    0.60
    RegressionTest
    0.59
    oa̍t
    0.59
    
    0.59
    Activations Density 0.561%

    No Known Activations