© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9923
    Prev
    Next
    INDEX
    Explanations

    HTML formatting tags, primarily paragraph and italics tags, especially those with hyphens and references

    oai_token-act-pair · gemini-2.0-flash

    HTML tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     OFDb
    -0.74
     للاسماء
    -0.62
    QMetaType
    -0.62
    DockStyle
    -0.58
    ########.
    -0.58
    gettime
    -0.56
     SafeMath
    -0.56
     estekak
    -0.55
    ThemeOverlay
    -0.55
     EClass
    -0.54
    POSITIVE LOGITS
    Hauptartikel
    0.40
    ftagPool
    0.39
    CreateMap
    0.37
     chi̍t
    0.37
    مزید
    0.37
     فريبيس
    0.36
     privée
    0.36
    SequentialGroup
    0.36
    ForTesting
    0.36
    帖最后由
    0.35
    Activations Density 0.597%

    No Known Activations