© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3453
    Prev
    Next
    INDEX
    Explanations

    medical terms and abbreviations, especially those related to eyes and certificates

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    apimachinery
    -0.74
    षण
    -0.56
    FunctionFlags
    -0.55
    fony
    -0.55
    thane
    -0.54
     zufolge
    -0.54
    Filmografia
    -0.53
    drawiam
    -0.53
    addContainerGap
    -0.53
     WaitForSeconds
    -0.52
    POSITIVE LOGITS
     also
    3.72
    also
    3.13
    Also
    2.94
     Also
    2.88
     también
    2.63
     também
    2.58
     også
    2.50
     также
    2.36
     également
    2.33
     ALSO
    2.31
    Activations Density 2.455%

    No Known Activations