© 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. 3596
    Prev
    Next
    INDEX
    Explanations

    descriptions of chemical synthesis steps

    oai_token-act-pair · gemini-2.0-flash

    chemical reactions or products

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

    chemical 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
    UserScript
    -0.82
    tvguidetime
    -0.75
    TypedDataSet
    -0.69
    ThroughAttribute
    -0.69
     démocr
    -0.67
    transQ
    -0.65
    featureID
    -0.65
    IndentedString
    -0.65
    fjspx
    -0.64
     propOrder
    -0.63
    POSITIVE LOGITS
    asu
    0.51
     فريبيس
    0.50
     round
    0.47
    حياتها
    0.47
     product
    0.47
     tre
    0.45
    \{\\
    0.42
     tr
    0.42
     us
    0.41
    tedly
    0.41
    Activations Density 2.501%

    No Known Activations