© 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. 10244
    Prev
    Next
    INDEX
    Explanations

    relative pronouns and words that often follow them

    oai_token-act-pair · gemini-2.0-flash

    terminology related to experts

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

    Experts

    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
    patreon
    -0.40
    requestBody
    -0.39
    umque
    -0.38
    éndole
    -0.38
    ंदीखरीदारी
    -0.38
     initComponents
    -0.36
     گفتم
    -0.36
     vorgestellt
    -0.35
    يانة
    -0.35
    rophes
    -0.35
    POSITIVE LOGITS
     experts
    2.38
    experts
    2.02
     analysts
    1.98
    Experts
    1.98
     Experts
    1.96
     scientists
    1.91
     researchers
    1.85
     expertos
    1.80
     Experten
    1.70
     specialists
    1.64
    Activations Density 3.152%

    No Known Activations