© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7314
    Prev
    Next
    INDEX
    Explanations

    text describing the Richter scale, often including "magnitude" and "scale"

    oai_token-act-pair · gemini-2.0-flash

    earthquake

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Pat
    -0.40
     alvo
    -0.39
     voting
    -0.38
     Course
    -0.38
     problemet
    -0.37
    Filmografia
    -0.36
     course
    -0.35
     tesoro
    -0.35
    Pat
    -0.35
     Voting
    -0.35
    POSITIVE LOGITS
     earthquake
    1.27
     earthquakes
    1.16
     Earthquake
    1.15
     quake
    0.99
    earth
    0.98
     Shake
    0.98
    Earthquake
    0.98
     tremors
    0.96
     seismo
    0.96
     seismic
    0.96
    Activations Density 0.413%

    No Known Activations