© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1959
    Prev
    Next
    INDEX
    Explanations

    terms used in software libraries

    oai_token-act-pair · gemini-2.0-flash

    programming libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    argout
    -0.92
    expandindo
    -0.91
    تقاوى
    -0.85
     contextLoads
    -0.82
    DockStyle
    -0.81
     consultato
    -0.81
    WaitGroup
    -0.80
    EDEFAULT
    -0.79
    FirstResponder
    -0.79
     chi̍t
    -0.77
    POSITIVE LOGITS
     arrivato
    0.47
    apd
    0.47
     veulent
    0.46
     mourut
    0.43
     venido
    0.43
     Pues
    0.41
     tit
    0.40
    <bos>
    0.40
     défend
    0.40
     venuto
    0.40
    Activations Density 1.714%

    No Known Activations