© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14349
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, specifically those used in UI development and error handling

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Small
    -1.13
     Private
    -1.09
     Natural
    -1.07
     Distant
    -1.07
     Large
    -1.05
     External
    -1.05
     Modern
    -1.05
     Non
    -1.05
     Traditional
    -1.05
     Permanent
    -1.04
    POSITIVE LOGITS
    ResponseWriter
    0.39
    TacToe
    0.39
    ToHex
    0.37
    ScrollPane
    0.33
    AndPassword
    0.32
     Edition
    0.32
     ThemeData
    0.32
    yntaxException
    0.31
     Assays
    0.30
    DialogComponent
    0.30
    Activations Density 6.135%

    No Known Activations