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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10107
    Prev
    Next
    INDEX
    Explanations

    words related to chemical processes in scientific research

    oai_token-act-pair · gemini-2.0-flash

    phrases related to biological processes and measurements

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

    binding/reaction processes

    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
     myſelf
    -1.10
     виправивши
    -1.01
     pleaſure
    -0.94
     itſelf
    -0.92
     betweenstory
    -0.92
     للاسماء
    -0.91
    ValueStyle
    -0.90
     Shakspeare
    -0.89
     Efq
    -0.89
     صوتيه
    -0.89
    POSITIVE LOGITS
     of
    0.76
     rate
    0.53
     mode
    0.52
     coefficient
    0.52
     cycle
    0.50
     be
    0.49
     co
    0.48
     style
    0.48
     chain
    0.47
     cintur
    0.47
    Activations Density 4.317%

    No Known Activations