© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3513
    Prev
    Next
    INDEX
    Explanations

    scientific writing or documents, particularly those involving experiment descriptions.

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    脚注の使い方
    -0.95
    ChildScrollView
    -0.87
     للمعارف
    -0.85
     Efq
    -0.82
     متعلقه
    -0.79
    KommentareTeilen
    -0.78
     itſelf
    -0.77
     يتيمه
    -0.72
    tanleria
    -0.71
     becauſe
    -0.71
    POSITIVE LOGITS
     the
    0.75
     Y
    0.62
     Z
    0.60
     
    0.59
     different
    0.58
     normal
    0.58
     M
    0.57
     this
    0.56
     selected
    0.56
     some
    0.53
    Activations Density 13.551%

    No Known Activations