© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11573
    Prev
    Next
    INDEX
    Explanations

    code and commands related to data transmission

    oai_token-act-pair · gemini-2.0-flash

    tx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    FX
    -0.61
    IOD
    -0.57
    dut
    -0.56
    SCO
    -0.56
    MX
    -0.56
    AX
    -0.56
    loed
    -0.55
    OCD
    -0.54
    BX
    -0.54
    IDs
    -0.54
    POSITIVE LOGITS
    DotNetBar
    0.90
     "..\..\..\
    0.77
     متعلقه
    0.77
     الرياضيه
    0.77
     فريبيس
    0.77
     estekak
    0.77
     turísticos
    0.71
    StoryboardSegue
    0.70
     Administrativna
    0.69
     "..\..\
    0.68
    Activations Density 1.303%

    No Known Activations