© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2248
    Prev
    Next
    INDEX
    Explanations

    words such as reports, experience and days (possibly related to memories)

    oai_token-act-pair · gemini-2.0-flash

    experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     defaultstate
    -0.73
     viewDidLoad
    -0.73
    Obrázky
    -0.71
    CppMethod
    -0.71
     kasarigan
    -0.69
     متعلقه
    -0.65
    findpost
    -0.65
    참고
    -0.64
    ValueStyle
    -0.63
     ModelExpression
    -0.63
    POSITIVE LOGITS
    <bos>
    0.47
    ScreenState
    0.45
     balanceOf
    0.44
    memoized
    0.41
    atoon
    0.38
     branches
    0.38
    slidesToShow
    0.38
    stateParams
    0.37
     properties
    0.37
    Pyx
    0.37
    Activations Density 1.564%

    No Known Activations