© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13322
    Prev
    Next
    INDEX
    Explanations

    a variety of sentence fragments lacking a consistent theme, possibly due to overtraining.

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    История
    -0.44
    onde
    -0.40
    RequestMapping
    -0.40
    textTheme
    -0.40
    Tags
    -0.39
    MatButtonModule
    -0.39
     onde
    -0.39
    NavigationBar
    -0.39
    flage
    -0.39
    caman
    -0.39
    POSITIVE LOGITS
     with
    1.80
     avec
    1.44
     WITH
    1.42
    with
    1.40
     With
    1.35
     dengan
    1.30
    With
    1.30
    WITH
    1.22
     với
    1.18
    avec
    1.15
    Activations Density 3.157%

    No Known Activations