© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6148
    Prev
    Next
    INDEX
    Explanations

    references to musical groups and performance

    oai_token-act-pair · gemini-2.0-flash

    band

    np_max-act · gemini-2.0-flash

    band Method used: 1 — identical max tokens; band

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     user
    -0.68
     propOrder
    -0.67
     if
    -0.58
    räume
    -0.57
     error
    -0.56
    MigrationBuilder
    -0.55
    UnusedPrivate
    -0.54
    帖最后由
    -0.54
     it
    -0.54
     del
    -0.53
    POSITIVE LOGITS
     photolibrary
    1.02
     ་་
    0.85
     strdup
    0.81
     ―――――
    0.81
     $_"
    0.80
    
    0.77
     (\<
    0.77
     Shakspeare
    0.73
     itſelf
    0.73
    .")
    0.73
    Activations Density 1.101%

    No Known Activations