© 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. 14016
    Prev
    Next
    INDEX
    Explanations

    a variety of words with seemingly no thematic connection

    oai_token-act-pair · gemini-2.0-flash

    direction

    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
     houſe
    -0.80
     Houſe
    -0.77
     Theſe
    -0.75
    CloseOperation
    -0.72
     Majefty
    -0.71
     preſent
    -0.70
    bukaan
    -0.69
    TagHelper
    -0.69
     Italijanski
    -0.69
    ंदीखरीदारी
    -0.68
    POSITIVE LOGITS
     United
    0.47
    歴
    0.46
    vän
    0.44
     respond
    0.43
    ïti
    0.43
    毯
    0.42
     саны
    0.42
     svar
    0.42
    дым
    0.42
     rising
    0.41
    Activations Density 7.695%

    No Known Activations