© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5991
    Prev
    Next
    INDEX
    Explanations

    the word "Asante," which is a healthcare provider in southern Oregon and northern California

    oai_token-act-pair · gemini-2.0-flash

    ante

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    en
    -0.72
    ante
    -0.71
     freilich
    -0.67
    y
    -0.64
    et
    -0.64
    ente
    -0.63
    a
    -0.62
    o
    -0.61
    in
    -0.59
    e
    -0.57
    POSITIVE LOGITS
    TagMode
    1.23
    expandindo
    1.05
    EDEFAULT
    1.04
     MainAxisSize
    1.04
    mybatisplus
    1.03
    ImageContext
    1.02
    igshid
    1.02
    Datuak
    0.98
    aarrggbb
    0.98
    Autoritní
    0.97
    Activations Density 0.820%

    No Known Activations