© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12803
    Prev
    Next
    INDEX
    Explanations

    legal and scientific terms often ending in "ed", "ised", "sed", "ing", or "able" that are related to study results, defense, or tolerance

    oai_token-act-pair · gemini-2.0-flash

    sed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    sed
    -0.73
     nos
    -0.59
    tion
    -0.55
     sed
    -0.52
    Nos
    -0.50
     Sed
    -0.49
    ree
    -0.48
    yn
    -0.48
    cios
    -0.47
    blockList
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.87
     Administrativna
    0.82
    ArrowToggle
    0.82
     >=",
    0.78
    }();
    0.73
    Tikang
    0.72
     '\\;'
    0.71
     ostavi
    0.71
     AssemblyCulture
    0.70
    Autoritní
    0.70
    Activations Density 7.619%

    No Known Activations