© 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. 9470
    Prev
    Next
    INDEX
    Explanations

    instances of somebody being told or not told something with an emphasis on the telling.

    oai_token-act-pair · gemini-2.0-flash

    telling or explaining

    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
    kkkk
    -0.46
    <bos>
    -0.43
     case
    -0.41
     GENERATED
    -0.41
    ImageContext
    -0.40
    Case
    -0.40
    rase
    -0.40
     vari
    -0.40
    控え
    -0.40
     numberWith
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.74
     Exacts
    0.72
    ftagPool
    0.72
     jsPsych
    0.71
     fallu
    0.67
     дописавши
    0.65
    المناصب
    0.63
    StructEnd
    0.63
     scolaires
    0.62
     skrift
    0.61
    Activations Density 2.991%

    No Known Activations