© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9773
    Prev
    Next
    INDEX
    Explanations

    chemical formulas, numbers, and related words, although the starts of sentences also seem to activate it

    oai_token-act-pair · gemini-2.0-flash

    4

    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
     pinulongan
    -0.79
    SystemColors
    -0.61
    anese
    -0.51
    DrawerToggle
    -0.49
    renderItem
    -0.48
    databind
    -0.47
    øver
    -0.44
    complexContent
    -0.44
     protoimpl
    -0.44
    CodedInputStream
    -0.43
    POSITIVE LOGITS
    fjspx
    0.87
     Paglinawan
    0.81
    StoryboardSegue
    0.79
    makeConstraints
    0.71
    tagHelperRunner
    0.69
    tvguidetime
    0.65
    antMatchers
    0.64
    jei
    0.64
     ProtoMessage
    0.64
    ьаж
    0.63
    Activations Density 0.873%

    No Known Activations