© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16383
    Prev
    Next
    INDEX
    Explanations

    the keyword "for" in code

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     daß
    -0.70
     (;;)
    -0.61
    Надо
    -0.56
     müßte
    -0.55
     oprot
    -0.55
    FontOfSize
    -0.54
     (;;
    -0.54
     läßt
    -0.51
     ]
    -0.51
     مشين
    -0.50
    POSITIVE LOGITS
    logrus
    0.66
    <bos>
    0.60
     welches
    0.60
    borderSide
    0.58
     welche
    0.57
     prends
    0.57
    TestingModule
    0.56
     welcher
    0.56
     impactful
    0.56
    Oft
    0.56
    Activations Density 0.389%

    No Known Activations