© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9635
    Prev
    Next
    INDEX
    Explanations

    words related to food, data, numbers, politics, energy bills, or human emotion.

    oai_token-act-pair · gemini-2.0-flash

    action verbs

    np_max-act-logits · gemini-2.0-flash

    verbs

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Be
    -0.47
    ']){
    -0.46
    Weiterlesen
    -0.46
    Diweddarwch
    -0.46
    )>=
    -0.45
    abestanden
    -0.43
     enfans
    -0.42
    windowFixed
    -0.42
    معلومات
    -0.42
    csolódó
    -0.41
    POSITIVE LOGITS
     come
    1.13
     turn
    1.00
     stop
    0.97
     leave
    0.97
     add
    0.97
     follow
    0.96
     start
    0.93
     bind
    0.92
     go
    0.90
     give
    0.90
    Activations Density 4.298%

    No Known Activations