© 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. 13019
    Prev
    Next
    INDEX
    Explanations

    seemingly random noun phrases

    oai_token-act-pair · gemini-2.0-flash

    word endings like 'ies' or related suffixes

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

    Babies/Families

    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
    principalColumn
    -0.84
    ագրություններ
    -0.73
    MENAFN
    -0.65
    XmlAccessorType
    -0.65
    liothèque
    -0.63
     بيها
    -0.62
    Personendaten
    -0.62
    Referències
    -0.62
     consultato
    -0.61
     chi̍t
    -0.61
    POSITIVE LOGITS
    sie
    0.71
    ers
    0.57
    sies
    0.52
     lenker
    0.52
     culoare
    0.50
    sey
    0.50
    ies
    0.50
     Dumnezeu
    0.48
    cy
    0.47
     cantit
    0.47
    Activations Density 1.368%

    No Known Activations