© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14109
    Prev
    Next
    INDEX
    Explanations

    java code syntax related to anonymous inner classes

    oai_token-act-pair · gemini-2.0-flash

    programming keywords and structures

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

    bracket

    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
    Not in Any Lists

    No Comments

    Negative Logits
     vapeur
    -0.58
    waltung
    -0.53
    contentValues
    -0.50
    ⎡
    -0.50
    tagHelperRunner
    -0.49
    oday
    -0.49
    gebn
    -0.49
    ostar
    -0.49
     szí
    -0.48
     åt
    -0.47
    POSITIVE LOGITS
    DispatchToProps
    0.60
     المعيارى
    0.59
    IntoConstraints
    0.56
     createState
    0.56
     مرئيه
    0.55
     pleaſure
    0.54
    DrawerToggle
    0.53
     myſelf
    0.52
     GenerationType
    0.52
     himſelf
    0.52
    Activations Density 4.237%

    No Known Activations