© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6993
    Prev
    Next
    INDEX
    Explanations

    words indicating an increase or decrease in quantity or level

    oai_token-act-pair · gemini-2.0-flash

    increase and decrease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     tombé
    -0.63
    municipi
    -0.60
     doigts
    -0.59
     Finishing
    -0.57
    XmlAccessType
    -0.57
     BorderSide
    -0.56
     découver
    -0.54
     nourrir
    -0.53
     marquées
    -0.53
     payé
    -0.53
    POSITIVE LOGITS
    <bos>
    1.03
     levels
    0.63
    TagMode
    0.60
     level
    0.53
     <=",
    0.52
    PreExecute
    0.51
     Level
    0.49
    AddTagHelper
    0.49
    asgi
    0.49
    atissimo
    0.48
    Activations Density 2.519%

    No Known Activations