© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7761
    Prev
    Next
    INDEX
    Explanations

    descriptions of a homeowner's association and activities within a neighborhood

    oai_token-act-pair · gemini-2.0-flash

    documentation/user content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Paglinawan
    -0.53
     Infórmanos
    -0.48
    tgär
    -0.47
    رشف
    -0.46
    wikidata
    -0.45
     pido
    -0.44
    okovic
    -0.43
    couverte
    -0.43
    requency
    -0.42
    balan
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    0.68
     XCTest
    0.68
     BorderRadius
    0.68
    __))
    0.63
    PerformLayout
    0.60
     estekak
    0.60
     useNavigate
    0.59
    AllowUser
    0.58
     Republics
    0.58
     exclusion
    0.57
    Activations Density 10.734%

    No Known Activations