© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3287
    Prev
    Next
    INDEX
    Explanations

    semicolons, parentheses and other code syntax

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     الحره
    -0.70
     classes
    -0.62
    Portail
    -0.57
     Clas
    -0.57
    CLASSES
    -0.56
    Perfectly
    -0.55
    utilisons
    -0.55
     amounts
    -0.53
     Classes
    -0.52
     Unito
    -0.49
    POSITIVE LOGITS
     
    0.63
    AppMethodBeat
    0.61
    AccessFile
    0.61
    WebVitals
    0.56
    GeneratedCode
    0.54
    artifactId
    0.51
     defaultstate
    0.50
    клопе
    0.50
     oiseaux
    0.50
    windowFixed
    0.49
    Activations Density 4.876%

    No Known Activations