© 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. 8341
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and figures

    oai_token-act-pair · gemini-2.0-flash

    words related to purpose or intention

    np_token-act-pair-logits · gpt-4o-mini
    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
    brary
    -0.58
    Personendaten
    -0.57
    DATABASES
    -0.55
     actionMode
    -0.55
     ContentValues
    -0.54
     мәкал
    -0.54
     Riche
    -0.53
     Waray
    -0.53
    inaires
    -0.52
     препратки
    -0.52
    POSITIVE LOGITS
    twimg
    0.70
    omyia
    0.53
     purpose
    0.48
     فريبيس
    0.47
     Purpose
    0.47
    Purpose
    0.47
    breos
    0.47
    AndEndTag
    0.46
    pielt
    0.45
    تقاوى
    0.45
    Activations Density 0.564%

    No Known Activations