© 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. 4131
    Prev
    Next
    INDEX
    Explanations

    words related to forming one's future through decisions

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terminology

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

    Spirituality, religion, internal being

    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
     consommateurs
    -0.60
     lèvres
    -0.56
     setId
    -0.54
     blessés
    -0.54
     spesa
    -0.53
    titleMargin
    -0.52
     distribuzione
    -0.52
     attentes
    -0.50
     efficaces
    -0.50
     publiques
    -0.49
    POSITIVE LOGITS
    ContentAsync
    0.64
    Autoritní
    0.64
     kaynağından
    0.64
    TargetException
    0.62
    SequentialGroup
    0.59
     pipeline
    0.58
     дописавши
    0.57
     GenerationType
    0.54
     ModelExpression
    0.52
     Gard
    0.52
    Activations Density 3.606%

    No Known Activations