© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5803
    Prev
    Next
    INDEX
    Explanations

    code snippets, annotations, or syntax from various programming languages

    oai_token-act-pair · gemini-2.0-flash

    Code-related

    np_max-act-logits · 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
     onCreateView
    -0.78
     Nowak
    -0.71
     Urqu
    -0.69
    findpost
    -0.68
     Pap
    -0.67
    webElementXpaths
    -0.67
    AutoScaleMode
    -0.66
    lande
    -0.65
     Dowling
    -0.65
     acceptez
    -0.64
    POSITIVE LOGITS
     \\
    0.40
     //
    0.40
     Forse
    0.38
    сылкі
    0.35
     Arhi
    0.33
     ////
    0.33
    PreExecute
    0.33
     sved
    0.32
     Arki
    0.31
     ALC
    0.31
    Activations Density 2.795%

    No Known Activations