© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1575
    Prev
    Next
    INDEX
    Explanations

    the start of the word "con", especially when capitalized

    oai_token-act-pair · gemini-2.0-flash

    terms starting with 'Con'

    np_token-act-pair-logits · gpt-4o-mini

    Con

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Rüyada
    -0.53
    ఞ
    -0.49
    deviantart
    -0.49
    stdafx
    -0.47
    はじめに
    -0.47
    covia
    -0.45
    Solic
    -0.44
    <u>
    -0.43
    bux
    -0.43
    chner
    -0.42
    POSITIVE LOGITS
     JpaRepository
    0.64
    SequentialGroup
    0.62
    Geplaatst
    0.57
     handleMessage
    0.56
     resourceCulture
    0.56
    RenderAtEndOf
    0.55
     Италијани
    0.55
     GenerationType
    0.54
    lapsingToolbar
    0.52
    crollView
    0.52
    Activations Density 0.559%

    No Known Activations