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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6269
    Prev
    Next
    INDEX
    Explanations

    lines of code that import libraries

    oai_token-act-pair · gemini-2.0-flash

    programming languages and imports

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

    import

    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
    IntoConstraints
    -0.74
     Majefty
    -0.67
     quæ
    -0.66
     Económica
    -0.63
     themſelves
    -0.61
     himſelf
    -0.58
    UpInside
    -0.57
     pleaſure
    -0.56
    .")]
    -0.56
    хьтан
    -0.56
    POSITIVE LOGITS
     "
    0.50
     xlink
    0.50
    irmingham
    0.49
     disambiguazione
    0.49
    #+#
    0.49
    writeFieldEnd
    0.48
     '
    0.48
     true
    0.48
    HomeAsUpEnabled
    0.47
     java
    0.47
    Activations Density 3.169%

    No Known Activations