© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8134
    Prev
    Next
    INDEX
    Explanations

    the word "for" in its various contexts, but also some other connecting words

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    rungsseite
    -0.63
    relativeTime
    -0.60
    ngdoc
    -0.57
    ädie
    -0.54
     montanha
    -0.53
    webElement
    -0.51
    templateUrl
    -0.51
    EDEFAULT
    -0.50
     esportes
    -0.50
    ãng
    -0.50
    POSITIVE LOGITS
    脚注の使い方
    0.56
    +#+#
    0.55
    :✨
    0.54
    IUrlHelper
    0.49
     kaynağından
    0.47
     essa
    0.46
     improved
    0.46
     мәкал
    0.45
     Improved
    0.44
    Improved
    0.43
    Activations Density 1.225%

    No Known Activations