© 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. 5601
    Prev
    Next
    INDEX
    Explanations

    technical documents including acronyms, measurements, percentages, and other figures

    oai_token-act-pair · gemini-2.0-flash

    technical or statistical terms

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

    statistical data

    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
     (
    -1.85
    (
    -1.19
     (.
    -1.13
    （
    -1.13
     ($
    -1.05
    .(
    -1.04
     (\
    -1.03
    。(
    -1.02
    ((
    -0.98
    }(
    -0.98
    POSITIVE LOGITS
    AndEndTag
    0.68
    ArrowToggle
    0.60
    IMPORTED
    0.51
     disponibilités
    0.51
    ãng
    0.49
     eenige
    0.49
     onCreateView
    0.49
     eenig
    0.49
     '-';
    0.48
    NOPQRST
    0.48
    Activations Density 4.014%

    No Known Activations