© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10211
    Prev
    Next
    INDEX
    Explanations

    references to the BBC along with some other words like News, Arts and Programmes

    oai_token-act-pair · gemini-2.0-flash

    BBC

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -0.85
     itſelf
    -0.79
     fevere
    -0.76
    styleable
    -0.76
     fhort
    -0.75
    UnsafeEnabled
    -0.70
     poffible
    -0.67
     pleaſure
    -0.67
    createCanvas
    -0.66
    MLLoader
    -0.64
    POSITIVE LOGITS
    wapV
    0.48
    Aiheesta
    0.41
    écuter
    0.40
    krä
    0.40
    рок
    0.40
     bun
    0.40
     gap
    0.38
    гиоз
    0.38
     mildly
    0.37
     bandas
    0.37
    Activations Density 0.904%

    No Known Activations