© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12343
    Prev
    Next
    INDEX
    Explanations

    the word "cache" along with words that often appear near it dealing with computer architecture

    oai_token-act-pair · gemini-2.0-flash

    read

    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
    formik
    -0.68
     виправивши
    -0.66
    migrationBuilder
    -0.60
    tvguidetime
    -0.60
     MainAxisSize
    -0.59
    TintMode
    -0.59
    ResponseWriter
    -0.57
     betweenstory
    -0.57
    WebElementEntity
    -0.57
    ScreenState
    -0.55
    POSITIVE LOGITS
     reads
    0.85
     read
    0.82
     Reads
    0.73
    reads
    0.71
     READ
    0.70
     reading
    0.70
     leitura
    0.70
     membaca
    0.66
    Reads
    0.66
    read
    0.66
    Activations Density 2.743%

    No Known Activations