© 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. 12501
    Prev
    Next
    INDEX
    Explanations

    terms related to software code and configuration

    oai_token-act-pair · gemini-2.0-flash

    Code properties/identifiers

    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
    GEBURTSDATUM
    -1.10
    ніципалі
    -1.03
    WriteBarrier
    -1.02
    kháu
    -1.00
    richTextPanel
    -0.99
     Normdatei
    -0.95
     &___
    -0.94
     AssemblyCompany
    -0.94
     '\\;'
    -0.92
     photolibrary
    -0.90
    POSITIVE LOGITS
     
    0.69
    )
    0.52
    all
    0.51
    ,
    0.51
     All
    0.50
    ).
    0.49
    .
    0.49
     all
    0.47
    All
    0.46
    .)
    0.44
    Activations Density 1.854%

    No Known Activations