© 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. 15967
    Prev
    Next
    INDEX
    Explanations

    various markup symbols, initialisms, and formatting elements specific to programming, math, and email.

    oai_token-act-pair · gemini-2.0-flash

    Web development, code, or html

    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
    ↵
    -1.14
    ↵↵
    -1.05
      
    -0.96
    ,
    -0.94
     (
    -0.91
     |
    -0.91
     to
    -0.88
     in
    -0.84
     the
    -0.84
     a
    -0.83
    POSITIVE LOGITS
    WebVitals
    1.20
     photolibrary
    1.15
    MLLoader
    1.14
     Efq
    1.13
    UserScript
    1.11
     anún
    1.10
     feroit
    1.09
     ་་
    1.05
     wikipagina
    1.05
    bootstrapcdn
    1.05
    Activations Density 7.111%

    No Known Activations