© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13539
    Prev
    Next
    INDEX
    Explanations

    the word "For" followed by additional words, particularly when used as an introductory phrase

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    argout
    -0.66
     For
    -0.61
     for
    -0.60
    For
    -0.54
    UseVisualStyle
    -0.53
     reach
    -0.50
     незавершена
    -0.49
    Portály
    -0.47
    Geplaatst
    -0.47
     Normdatei
    -0.47
    POSITIVE LOGITS
     walnuts
    0.59
    mány
    0.59
     bezeichneter
    0.56
     Chriftian
    0.56
    ésult
    0.54
    ngdoc
    0.54
    Inspec
    0.53
    عالی
    0.53
    ürm
    0.53
     themſelves
    0.53
    Activations Density 1.186%

    No Known Activations