© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15001
    Prev
    Next
    INDEX
    Explanations

    table and equation references

    oai_token-act-pair · gemini-2.0-flash

    code and technical notations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     مواليد
    -0.54
    cotti
    -0.45
    tivité
    -0.42
     itong
    -0.41
    lits
    -0.40
    々木
    -0.40
    tive
    -0.40
    som
    -0.39
    laceae
    -0.39
     Mémoires
    -0.39
    POSITIVE LOGITS
    +#+#
    1.14
     Wicidata
    1.05
     AspNetCore
    1.04
     فريبيس
    1.03
    NameInMap
    0.98
    +#+
    0.96
    bootstrapcdn
    0.95
    contentLoaded
    0.94
    webElementXpaths
    0.94
    цездатний
    0.90
    Activations Density 2.666%

    No Known Activations