© 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. 2987
    Prev
    Next
    INDEX
    Explanations

    html character codes

    oai_token-act-pair · gemini-2.0-flash

    say numbers

    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
     المعيارى
    -0.56
    costal
    -0.52
     McDonough
    -0.51
     كومونز
    -0.49
    AnimationFrame
    -0.49
    basicConfig
    -0.49
     Zapata
    -0.47
    urten
    -0.46
    SceneManagement
    -0.45
     Retail
    -0.43
    POSITIVE LOGITS
     perſon
    0.61
     Eſ
    0.60
     Majefty
    0.60
     Efq
    0.59
     dieß
    0.59
     Anſ
    0.59
     purpoſe
    0.58
     dezelve
    0.58
     Púb
    0.58
     ſame
    0.57
    Activations Density 1.563%

    No Known Activations