© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12105
    Prev
    Next
    INDEX
    Explanations

    words and phrases which evoke an adventure theme

    oai_token-act-pair · gemini-2.0-flash

    Abstract boundaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    +#+#
    -0.80
     dAtA
    -0.73
    ConstraintMaker
    -0.65
    addContainerGap
    -0.64
    APORE
    -0.63
     onOptions
    -0.61
    <bos>
    -0.57
     OBITUARY
    -0.56
    ///</
    -0.56
    IsRequired
    -0.55
    POSITIVE LOGITS
     katun
    0.50
    kovi
    0.50
     sepen
    0.50
     slicer
    0.49
    esinde
    0.49
     шпа
    0.49
    ESY
    0.49
    Spooky
    0.48
    Scrolling
    0.48
    NewUrlParser
    0.48
    Activations Density 0.898%

    No Known Activations