© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12594
    Prev
    Next
    INDEX
    Explanations

    distances expressed in kilometers, possibly associated with experiments or studies

    oai_token-act-pair · gemini-2.0-flash

    distance measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     miles
    -1.28
     mile
    -1.15
    miles
    -1.03
     millimeter
    -0.98
    mile
    -0.97
     MILES
    -0.96
     yards
    -0.95
     lbs
    -0.95
     millimeters
    -0.95
     Mile
    -0.94
    POSITIVE LOGITS
     createState
    0.52
     raya
    0.48
    {~
    0.47
    HasForeignKey
    0.46
    fbox
    0.43
     entradas
    0.43
     totiž
    0.43
    麟
    0.42
     couche
    0.42
    ]))
    0.42
    Activations Density 1.518%

    No Known Activations