© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6486
    Prev
    Next
    INDEX
    Explanations

    instances of the word "part" or "place" or the abbreviation "WA" which are often associated with events

    oai_token-act-pair · gemini-2.0-flash

    events occurring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -1.49
     myſelf
    -1.47
     Jefus
    -1.38
     Majefty
    -1.38
    ſelf
    -1.30
     Efq
    -1.30
     himſelf
    -1.29
     purpoſe
    -1.27
     raiſ
    -1.25
    ſelves
    -1.24
    POSITIVE LOGITS
    <eos>
    0.81
     “
    0.77
    ,
    0.75
    ↵↵
    0.73
     a
    0.73
     de
    0.73
     (
    0.71
     ‘
    0.71
     ed
    0.69
    /
    0.67
    Activations Density 0.102%

    No Known Activations