© 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. 8426
    Prev
    Next
    INDEX
    Explanations

    substrings within citations, specifically titles of publications and journal names, along with other publication-related terms such as 'http,' 'doi,' and 'org.'

    oai_token-act-pair · gemini-2.0-flash

    Academic references

    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
    SharedCtor
    -0.79
    featureID
    -0.68
    FunctionFlags
    -0.62
    eachtet
    -0.62
     nakalista
    -0.61
    NameInMap
    -0.59
    קישורים
    -0.53
    
    -0.53
    //
    -0.52
    ifor
    -0.51
    POSITIVE LOGITS
    CloseOperation
    0.55
    +#+
    0.54
     estimés
    0.50
    ẨM
    0.50
     ब्रेकडाउन
    0.48
     Longitude
    0.47
     unti
    0.47
    fjspx
    0.47
    memoized
    0.46
    UnusedPrivate
    0.46
    Activations Density 0.684%

    No Known Activations