© 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. 11500
    Prev
    Next
    INDEX
    Explanations

    a strange mix of words that seem related to medical terminology, geography/politics and manufacturing/chemistry.

    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
    SequentialGroup
    -1.07
    ⓧ
    -1.04
    WillAppear
    -0.93
    MigrationBuilder
    -0.90
     дописавши
    -0.89
     '\\;'
    -0.89
    IsContent
    -0.87
    InjectAttribute
    -0.85
    __':
    -0.81
    ="@+
    -0.81
    POSITIVE LOGITS
     aikaa
    0.56
    produzione
    0.42
    是多少
    0.42
     altrett
    0.41
     meille
    0.41
     halbe
    0.40
    我知道
    0.37
     troviamo
    0.37
     among
    0.37
     vainqueur
    0.37
    Activations Density 9.180%

    No Known Activations