© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2750
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and," often preceded by "oh", "well", or a comma

    oai_token-act-pair · gemini-2.0-flash

    and

    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
     ModelExpression
    -0.76
    期刊论文
    -0.73
    +#+#
    -0.71
     AssemblyProduct
    -0.68
    prepareStatement
    -0.63
    zelfde
    -0.61
     serializers
    -0.60
    ConstraintMaker
    -0.60
     ExecuteAsync
    -0.59
    存于互联网档案馆
    -0.58
    POSITIVE LOGITS
     mergeFrom
    0.52
    FunctionFlags
    0.51
    kedés
    0.49
    WindowListener
    0.47
    torta
    0.44
    fiche
    0.44
    barung
    0.43
    MANS
    0.42
    RSV
    0.42
    getRepository
    0.42
    Activations Density 2.488%

    No Known Activations