© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13246
    Prev
    Next
    INDEX
    Explanations

    Java or Python code, especially related to web apps and frameworks

    oai_token-act-pair · gemini-2.0-flash

    springframework

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     kasarigan
    -0.59
    はじめに
    -0.58
    AutoScaleMode
    -0.57
    InteropServices
    -0.57
     <<<<<<<<<<<<<<
    -0.56
     kaynağından
    -0.52
    XMLSchema
    -0.51
     onCreateView
    -0.51
    BackPressed
    -0.50
     CreateTagHelper
    -0.49
    POSITIVE LOGITS
     ویکی‌پدیا
    0.50
     sanitaires
    0.47
     Tasche
    0.42
     étan
    0.40
     Relaciones
    0.39
    ędziesz
    0.39
     enfans
    0.39
     mérit
    0.38
    photobucket
    0.36
     définiti
    0.36
    Activations Density 0.206%

    No Known Activations