© 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. 10283
    Prev
    Next
    INDEX
    Explanations

    technical terms from chemistry and physics

    oai_token-act-pair · gemini-2.0-flash

    scientific experiments

    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
    StoryboardSegue
    -0.64
     contextLoads
    -0.63
     typelib
    -0.59
     المعيارى
    -0.57
     himo
    -0.57
     Counters
    -0.55
    orrhage
    -0.52
    liferation
    -0.52
    GOTREF
    -0.51
    IVEREF
    -0.51
    POSITIVE LOGITS
     minimum
    0.59
    <bos>
    0.59
     seuil
    0.52
     range
    0.52
    RTSC
    0.51
     min
    0.49
     recipe
    0.48
    GetAxis
    0.47
    AddTagHelper
    0.47
     target
    0.47
    Activations Density 2.626%

    No Known Activations