© 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. 13733
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "ict" or "ect" that are preceded by "pred" or "inf"

    oai_token-act-pair · gemini-2.0-flash

    infection and adaptation

    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
    WebVitals
    -1.07
    expandindo
    -1.01
     estekak
    -0.93
     EconPapers
    -0.93
     betweenstory
    -0.86
     مشين
    -0.85
    +#+#
    -0.84
    AddTagHelper
    -0.83
    InjectMocks
    -0.81
    帖最后由
    -0.80
    POSITIVE LOGITS
     schermo
    0.43
    st
    0.43
     razão
    0.39
    θος
    0.38
     tavola
    0.38
    stub
    0.37
    écran
    0.37
    理
    0.37
    mety
    0.37
    run
    0.36
    Activations Density 1.371%

    No Known Activations