© 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. 14371
    Prev
    Next
    INDEX
    Explanations

    terms related to law, medicine, disability and discrimination

    oai_token-act-pair · gemini-2.0-flash

    Special topics

    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
    ConstraintMaker
    -0.83
    évaluateur
    -0.68
    berdayakan
    -0.64
     AssemblyCulture
    -0.63
    /**
    -0.62
    SourceChecksum
    -0.62
    setOnAction
    -0.60
    reportWebVitals
    -0.59
     mauva
    -0.59
     quelcon
    -0.58
    POSITIVE LOGITS
    -
    0.50
     depository
    0.42
     strategist
    0.42
     coalitions
    0.42
     nawr
    0.41
     tabulation
    0.40
     planner
    0.39
     edition
    0.39
     assemblage
    0.39
    ‐
    0.38
    Activations Density 12.978%

    No Known Activations