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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11126
    Prev
    Next
    INDEX
    Explanations

    the word "occur" and other words indicative that something happens

    oai_token-act-pair · gemini-2.0-flash

    occur

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     occurred
    -2.22
     occurs
    -2.20
     occur
    -2.19
    occur
    -1.94
     occurring
    -1.92
     Occur
    -1.90
    occurs
    -1.88
     occured
    -1.76
     occurrence
    -1.71
    Occur
    -1.49
    POSITIVE LOGITS
     Réponses
    0.67
    InitVars
    0.58
     تضيفلها
    0.57
     repres
    0.57
    󠁢
    0.57
     trajets
    0.56
     विश्वसनीयता
    0.54
    |}{}
    0.54
    DockStyle
    0.54
     DISTR
    0.54
    Activations Density 2.208%

    No Known Activations