© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7498
    Prev
    Next
    INDEX
    Explanations

    strings of text that are references, such as journal articles or reports, along with words associated with studies

    oai_token-act-pair · gemini-2.0-flash

    scientific research papers

    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
     soft
    -0.48
    liothèque
    -0.45
    colgroup
    -0.43
     Soft
    -0.41
    WriteByte
    -0.41
    soft
    -0.39
    rolled
    -0.39
     hard
    -0.39
     digital
    -0.38
    binant
    -0.38
    POSITIVE LOGITS
     nahilalakip
    1.12
    TargetException
    0.77
     שוליים
    0.70
     oprot
    0.68
     يتيمه
    0.68
    oredCriteria
    0.68
     مشين
    0.67
    ScopeManager
    0.66
    CodeAttribute
    0.66
    PreferredItem
    0.66
    Activations Density 3.180%

    No Known Activations