© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12901
    Prev
    Next
    INDEX
    Explanations

    the degree symbol and nearby numbers

    oai_token-act-pair · gemini-2.0-flash

    circ

    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
    circ
    -1.78
     circ
    -1.28
     Circ
    -1.17
    Circ
    -1.03
    <bos>
    -1.02
     circulate
    -0.92
     circulating
    -0.90
     CIRC
    -0.81
     المعيارى
    -0.80
     circulation
    -0.80
    POSITIVE LOGITS
     dép
    0.46
    toThrow
    0.45
     μή
    0.45
     den
    0.44
     coque
    0.44
    êmes
    0.43
     ansehen
    0.42
    ACIONAL
    0.41
    ANTLR
    0.41
    AnchorStyles
    0.41
    Activations Density 2.948%

    No Known Activations