© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12700
    Prev
    Next
    INDEX
    Explanations

    text discussing hardship and violence in Nigeria.

    oai_token-act-pair · gemini-2.0-flash

    Detailed report excerpts

    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
    ();)
    -0.53
    timewa
    -0.45
    ۇ
    -0.43
     champignons
    -0.43
     nemlig
    -0.41
    fcntl
    -0.41
     supérieures
    -0.40
     olympiques
    -0.40
     âgées
    -0.40
    sula
    -0.39
    POSITIVE LOGITS
    IndentedString
    0.80
    StreetMap
    0.77
    DoubleQuotes
    0.76
    parsedMessage
    0.76
    ArrowToggle
    0.72
     الاطلاع
    0.71
     nahilalakip
    0.71
    WithIOException
    0.71
    存于互联网档案馆
    0.71
    webElementXpaths
    0.69
    Activations Density 0.905%

    No Known Activations