© 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. 13124
    Prev
    Next
    INDEX
    Explanations

    terms related to software or events of civil unrest

    oai_token-act-pair · gemini-2.0-flash

    French verbs

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

    Legal/workplace contexts

    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
     makers
    -0.82
    izers
    -0.81
     maker
    -0.80
     searcher
    -0.79
    izer
    -0.79
     builders
    -0.79
    isers
    -0.78
    setter
    -0.76
     builder
    -0.75
     communicator
    -0.75
    POSITIVE LOGITS
     défendre
    0.71
     satisfaire
    0.64
     remplacé
    0.61
     peindre
    0.59
     refusé
    0.59
     couvrir
    0.58
     soutenu
    0.58
     préc
    0.58
     reú
    0.57
     marquées
    0.57
    Activations Density 1.095%

    No Known Activations