© 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. 4727
    Prev
    Next
    INDEX
    Explanations

    references to real estate demolition, books in the library, and automobile auctions

    oai_token-act-pair · gemini-2.0-flash

    items are missing

    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
     nakalista
    -0.79
     kaarangay
    -0.66
    RegressionTest
    -0.65
    ftagPool
    -0.65
    Geplaatst
    -0.63
    principalColumn
    -0.60
    IntoConstraints
    -0.60
    Тарихы
    -0.59
    tagHelperRunner
    -0.57
     <",
    -0.57
    POSITIVE LOGITS
    anyol
    0.53
     censiti
    0.47
    rawDesc
    0.46
    Portail
    0.42
    सन्दर्भ
    0.40
     ولد
    0.40
    Referencias
    0.40
    كين
    0.38
    nál
    0.37
     apo
    0.37
    Activations Density 2.803%

    No Known Activations