© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15609
    Prev
    Next
    INDEX
    Explanations

    language relating to raising or providing money/funding/investment

    oai_token-act-pair · gemini-2.0-flash

    Funding and revenue

    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
     CanadaChoose
    -0.48
    SPO
    -0.46
    ineno
    -0.46
    windowFixed
    -0.44
    batis
    -0.44
    bai
    -0.43
    CopyWith
    -0.43
    quiao
    -0.43
    badan
    -0.43
     perfettamente
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.71
     gyhoeddwyd
    0.68
    RegressionTest
    0.65
    NegativeButton
    0.63
    "])
    0.57
     تانيه
    0.55
     "'");
    0.54
    JKLM
    0.54
    '])
    0.54
    Lähteet
    0.53
    Activations Density 1.861%

    No Known Activations