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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14222
    Prev
    Next
    INDEX
    Explanations

    nouns with multiple modifiers

    oai_token-act-pair · gemini-2.0-flash

    Scientific passages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    +#+#
    -0.85
     autorytatywna
    -0.79
    InvalidProtocol
    -0.71
     otomatig
    -0.71
     kasarigan
    -0.66
    MessageTagHelper
    -0.64
     ligiloj
    -0.63
    ConstraintMaker
    -0.63
    الإنجليزية
    -0.59
     betweenstory
    -0.59
    POSITIVE LOGITS
    λίου
    0.54
     delas
    0.50
    dataProvider
    0.47
     outdoors
    0.47
    PositiveButton
    0.46
     is
    0.45
    orong
    0.45
    다고
    0.45
    idist
    0.45
    灌
    0.44
    Activations Density 4.747%

    No Known Activations