© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5542
    Prev
    Next
    INDEX
    Explanations

    words related to previous, outside, or former, alongside the word expert

    oai_token-act-pair · gemini-2.0-flash

    experts

    np_max-act · gemini-2.0-flash

    experts

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     "..\..\..\
    -0.91
    complexContent
    -0.90
    PerformLayout
    -0.87
     createSlice
    -0.82
    انجليز
    -0.82
     ModelExpression
    -0.78
    omitempty
    -0.76
     mergeFrom
    -0.75
    AndEndTag
    -0.74
     متعلقه
    -0.73
    POSITIVE LOGITS
    <bos>
    0.84
     superiori
    0.69
     commerciali
    0.68
     Improved
    0.65
     itſelf
    0.63
     supérieurs
    0.62
     Tosh
    0.60
     fons
    0.59
     hasard
    0.58
     Efq
    0.58
    Activations Density 2.931%

    No Known Activations