© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8357
    Prev
    Next
    INDEX
    Explanations

    references and mentions of scientific concepts

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming entities

    np_token-act-pair-logits · gpt-4o-mini

    movement and physics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     llevan
    -0.52
     haga
    -0.49
     lleva
    -0.47
     diversa
    -0.46
    preventDefault
    -0.43
     momento
    -0.41
     onResponse
    -0.41
     automatiques
    -0.40
     âgé
    -0.40
     desempen
    -0.40
    POSITIVE LOGITS
    UnsafeEnabled
    0.83
     חיצוניים
    0.74
     okuyayım
    0.71
    ConstraintMaker
    0.70
    JsonHelper
    0.69
    featureID
    0.69
    IndentedString
    0.69
    nemia
    0.69
     vehicle
    0.69
    tagHelperRunner
    0.69
    Activations Density 7.585%

    No Known Activations