© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15404
    Prev
    Next
    INDEX
    Explanations

    sentences where a person or thing is described

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     allowed
    -0.75
     charged
    -0.62
    Allowed
    -0.61
    allowed
    -0.61
     propOrder
    -0.60
     Charged
    -0.60
    basicConfig
    -0.60
     permitted
    -0.58
     مشين
    -0.57
     Allowed
    -0.56
    POSITIVE LOGITS
     chamada
    0.52
     called
    0.51
     unknownFields
    0.50
    ressum
    0.49
     chamado
    0.48
    reservation
    0.46
    aarrggbb
    0.46
    ViewSet
    0.46
    kloped
    0.45
    Advertisement
    0.45
    Activations Density 2.559%

    No Known Activations