© 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. 6476
    Prev
    Next
    INDEX
    Explanations

    words ending in "ed", "ly", or related to science/technology with an emphasis on l/v/s and also military terms

    oai_token-act-pair · gemini-2.0-flash

    vs

    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
    RenderAtEndOf
    -0.89
    /*---
    -0.82
    évaluateur
    -0.81
    GEBURTSDATUM
    -0.79
    uxxxx
    -0.79
    IndentedString
    -0.77
    SharedCtor
    -0.76
    SourceChecksum
    -0.74
     متعلقه
    -0.72
    Personendaten
    -0.71
    POSITIVE LOGITS
    addContainerGap
    0.51
     core
    0.43
     VARI
    0.43
    getMenuInflater
    0.42
    LayoutInflater
    0.39
     Core
    0.39
     član
    0.39
    îtra
    0.38
    addGap
    0.38
    lin
    0.38
    Activations Density 9.374%

    No Known Activations