© 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. 5590
    Prev
    Next
    INDEX
    Explanations

    descriptive language setting the scene for a novel or short story

    oai_token-act-pair · gemini-2.0-flash

    non-standard spelling or unique prefixes

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

    small

    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
    powers
    -0.46
     cez
    -0.43
    rawQuery
    -0.41
     hàng
    -0.38
     an
    -0.38
     könnten
    -0.37
    iban
    -0.36
    ewa
    -0.36
    aban
    -0.36
     baru
    -0.35
    POSITIVE LOGITS
     Efq
    0.92
    ValueStyle
    0.91
     myſelf
    0.90
    mybatisplus
    0.88
     ſmall
    0.88
     Majefty
    0.86
     purpoſe
    0.85
     ſche
    0.84
     Monfieur
    0.83
     Reſ
    0.81
    Activations Density 1.726%

    No Known Activations