© 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. 3257
    Prev
    Next
    INDEX
    Explanations

    the beginning of Android code samples

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

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

    Code and Android

    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
    SourceChecksum
    -0.65
    nofollow
    -0.53
    ModelAdmin
    -0.46
     CENTRAL
    -0.45
     Private
    -0.45
     зер
    -0.43
    indrome
    -0.43
    addCriterion
    -0.43
    XmlAccessType
    -0.42
     frame
    -0.42
    POSITIVE LOGITS
     TextInputType
    0.65
     الاطلاع
    0.61
    GEBURTSDATUM
    0.59
    ViewFeatures
    0.52
    jadwal
    0.52
    ISupport
    0.50
     juſ
    0.50
     jue
    0.49
    estly
    0.49
    izeit
    0.49
    Activations Density 0.202%

    No Known Activations