© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9592
    Prev
    Next
    INDEX
    Explanations

    what appears to be the word "if", as well as possibly the letters "IG" in some contexts

    oai_token-act-pair · gemini-2.0-flash

    if

    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
    Negative Logits
    TemporalType
    -0.66
    ]")]
    -0.63
    balleur
    -0.58
     nahilalakip
    -0.58
    contentLoaded
    -0.57
    SceneManagement
    -0.57
     saha
    -0.57
    InputBorder
    -0.56
    yntaxException
    -0.56
    octubre
    -0.55
    POSITIVE LOGITS
     Chi
    0.63
    Chi
    0.63
    ">//
    0.60
    hie
    0.56
    CHI
    0.56
    chie
    0.55
     CHI
    0.55
    jooq
    0.54
    hi
    0.53
     Hi
    0.53
    Activations Density 0.200%

    No Known Activations