© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8532
    Prev
    Next
    INDEX
    Explanations

    statistical analysis results (confidence intervals, p-values, odds ratios)

    oai_token-act-pair · gemini-2.0-flash

    CI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     itſelf
    -1.14
     betweenstory
    -1.13
     myſelf
    -1.09
    MigrationBuilder
    -1.05
     ſeveral
    -0.99
     Theſe
    -0.95
     purpoſe
    -0.93
     препратки
    -0.93
     otomatig
    -0.91
     pleaſure
    -0.90
    POSITIVE LOGITS
     
    0.51
    </em>
    0.48
     “
    0.48
     "
    0.48
     his
    0.47
    .
    0.46
    _
    0.46
    “
    0.44
    '
    0.44
    ((
    0.43
    Activations Density 1.391%

    No Known Activations