© 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. 14192
    Prev
    Next
    INDEX
    Explanations

    verbs related to mathematical probability alongside words related to providing/creating

    oai_token-act-pair · gemini-2.0-flash

    self-referential terms or concepts

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

    Probability calculations with replacement

    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
    AsUp
    -0.74
    webElementXpaths
    -0.73
    +#+#
    -0.66
     nakalista
    -0.64
    enumi
    -0.63
     <<<<<<<<<<<<<<
    -0.62
    UserScript
    -0.61
     referenties
    -0.60
     convertView
    -0.60
     ویکی‌پدی
    -0.59
    POSITIVE LOGITS
     itſelf
    0.79
     مواليد
    0.77
     becauſe
    0.65
     myſelf
    0.65
     ujednoznacz
    0.65
     itong
    0.59
    Décès
    0.58
     fufficient
    0.57
     againſt
    0.56
     himſelf
    0.56
    Activations Density 9.507%

    No Known Activations