© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9415
    Prev
    Next
    INDEX
    Explanations

    language related to scientific studies and research.

    oai_token-act-pair · gemini-2.0-flash

    forms of the word 'combine'

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

    Research methodologies

    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
     based
    -0.57
    authored
    -0.54
    based
    -0.52
     BASED
    -0.50
     Based
    -0.50
    MessageOf
    -0.47
    UALA
    -0.47
     huma
    -0.47
     authored
    -0.46
    Marko
    -0.45
    POSITIVE LOGITS
     combine
    1.05
    Combine
    0.99
     combines
    0.96
     combining
    0.94
    combine
    0.94
     Combine
    0.88
     Combining
    0.82
    Combining
    0.80
    TagMode
    0.78
     combin
    0.73
    Activations Density 3.906%

    No Known Activations