© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4480
    Prev
    Next
    INDEX
    Explanations

    mentions of the number two or four and things associated with those numbers like "for" or "shared by two"

    oai_token-act-pair · gemini-2.0-flash

    two

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     once
    -0.75
     ONCE
    -0.63
    once
    -0.60
     Once
    -0.58
    ONCE
    -0.56
    Once
    -0.54
     sekali
    -0.51
    Nationalité
    -0.51
    opoly
    -0.50
    الإنجليزية
    -0.50
    POSITIVE LOGITS
     two
    0.93
    two
    0.82
    Two
    0.77
     Two
    0.73
    TWO
    0.71
     TWO
    0.66
     deux
    0.64
     dvou
    0.61
     dois
    0.61
     két
    0.60
    Activations Density 1.332%

    No Known Activations