© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11426
    Prev
    Next
    INDEX
    Explanations

    qualifications or conditions using phrases such as "such as", "that", "or", and "including"

    oai_token-act-pair · gemini-2.0-flash

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Nacionales
    -0.51
     nagu
    -0.51
    lès
    -0.47
    fractive
    -0.47
    antaranya
    -0.46
     például
    -0.45
     grossa
    -0.45
     versioni
    -0.44
     ég
    -0.43
     recensioni
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.77
    ngdoc
    0.73
    cèse
    0.71
    setopt
    0.70
     незавершена
    0.69
    TagMode
    0.67
    出版年
    0.66
    AxisAlignment
    0.66
    routeProvider
    0.66
     Reap
    0.66
    Activations Density 11.873%

    No Known Activations