© 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. 2555
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to abbreviations, references and denotation

    oai_token-act-pair · 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
    adaptiveStyles
    -0.93
    StructEnd
    -0.88
    PMailer
    -0.87
    elemField
    -0.79
    AsUp
    -0.79
    transQ
    -0.79
     للمعارف
    -0.78
    dafx
    -0.77
     שוליים
    -0.77
    __*/
    -0.75
    POSITIVE LOGITS
    S
    0.48
    T
    0.47
     darb
    0.44
    aster
    0.43
    paksa
    0.43
    P
    0.41
    yo
    0.40
    ni
    0.40
    si
    0.39
    â
    0.39
    Activations Density 1.802%

    No Known Activations