© 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. 15643
    Prev
    Next
    INDEX
    Explanations

    terms related to architecture, construction, and real estate.

    oai_token-act-pair · gemini-2.0-flash

    Interiors

    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
     AssemblyCulture
    -0.77
    makeText
    -0.65
    VersionUID
    -0.62
     NSCoder
    -0.59
    IsContent
    -0.58
     kaarangay
    -0.58
    StructEnd
    -0.56
     frais
    -0.52
    )}</
    -0.49
    resave
    -0.49
    POSITIVE LOGITS
     leading
    0.64
     Leading
    0.63
     off
    0.60
    Leading
    0.59
    LEADING
    0.56
     lead
    0.53
    Lead
    0.52
    hdessä
    0.52
    ույ
    0.52
    rakech
    0.52
    Activations Density 6.202%

    No Known Activations