© 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. 5466
    Prev
    Next
    INDEX
    Explanations

    words that contain the letters 'r', 'y', 'h', 's', 't', 'j', 'd' in them

    oai_token-act-pair · gemini-2.0-flash

    historical and political events

    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
    SharedDtor
    -0.77
    :✨
    -0.77
    Personendaten
    -0.75
    mergeFrom
    -0.72
    twimg
    -0.71
     &___
    -0.69
    autoIncrement
    -0.66
    niająca
    -0.65
    webElementXpaths
    -0.65
    tagHelperRunner
    -0.65
    POSITIVE LOGITS
    UseVisualStyle
    0.51
    idel
    0.50
    substantial
    0.49
     eccell
    0.47
    A
    0.47
    so
    0.45
     trecut
    0.45
    Insn
    0.44
    canestro
    0.43
    тельства
    0.43
    Activations Density 1.005%

    No Known Activations