© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14623
    Prev
    Next
    INDEX
    Explanations

    the word, or phrase, "if"

    oai_token-act-pair · gemini-2.0-flash

    conditional words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     يتيمه
    -0.74
    fortawesome
    -0.63
    sizeCache
    -0.60
    الحياه
    -0.59
    Билгалдахарш
    -0.57
     informée
    -0.57
    gonic
    -0.56
    Enllaços
    -0.55
     intptr
    -0.55
    Cyfeiriadau
    -0.55
    POSITIVE LOGITS
    Rè
    0.63
     memorized
    0.52
     colorless
    0.51
    häuse
    0.50
     Baillargeon
    0.48
     voorzien
    0.48
     pleaſure
    0.47
     Else
    0.47
     memorize
    0.47
    如果不是
    0.46
    Activations Density 0.776%

    No Known Activations