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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10951
    Prev
    Next
    INDEX
    Explanations

    mentions of people moving from one place to another, family relations, birth, death and biographical information in general

    oai_token-act-pair · gemini-2.0-flash

    Moved

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     surla
    -0.90
    onViewCreated
    -0.76
    ########.
    -0.67
    tvguidetime
    -0.67
    揄
    -0.66
    DllImport
    -0.65
    tagHelperRunner
    -0.63
    ChildScrollView
    -0.62
    tagHelper
    -0.61
    writeFieldEnd
    -0.61
    POSITIVE LOGITS
     to
    0.63
    UnusedPrivate
    0.48
    :^(
    0.48
    tois
    0.43
    entid
    0.42
    得
    0.41
    nelse
    0.41
     strá
    0.41
     here
    0.40
    uesia
    0.40
    Activations Density 4.283%

    No Known Activations