© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5852
    Prev
    Next
    INDEX
    Explanations

    text discussing changes in housing and real estate

    oai_token-act-pair · gemini-2.0-flash

    housing and construction

    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
    레이
    -0.44
    cyto
    -0.44
    coltura
    -0.44
    äj
    -0.43
     hason
    -0.43
    acen
    -0.42
    grunn
    -0.42
    PathVariable
    -0.42
    マジ
    -0.42
    arc
    -0.41
    POSITIVE LOGITS
    UserScript
    0.82
    IUrlHelper
    0.74
    хьтан
    0.72
    WriteBarrier
    0.71
     flats
    0.71
    نیم
    0.68
    modelBuilder
    0.68
    MemoryWarning
    0.68
    KommentareTeilen
    0.68
     AssemblyCulture
    0.66
    Activations Density 2.026%

    No Known Activations