© 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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 12570
    Prev
    Next
    INDEX
    Explanations

    the word "times" and also sometimes finds places where an event happens to a 'victim' or action, or 'wing'

    oai_token-act-pair · gemini-2.0-flash

    times

    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
     times
    -2.47
    Times
    -1.92
    times
    -1.91
     Times
    -1.80
     TIMES
    -1.73
    TIMES
    -1.60
     veces
    -1.51
     twice
    -1.16
     occasions
    -1.16
     vezes
    -1.13
    POSITIVE LOGITS
    妥
    0.51
     passo
    0.49
     rata
    0.48
     âgées
    0.48
    InSection
    0.48
    RemoveAt
    0.47
    IElement
    0.46
     genie
    0.46
     voeten
    0.46
     Twelve
    0.45
    Activations Density 3.132%

    No Known Activations