© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3446
    Prev
    Next
    INDEX
    Explanations

    a variety of non-linguistic patterns, including indentation, numbers, bullets, and the start of a quote

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · 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
     myſelf
    -1.18
     Monfieur
    -1.12
     pleaſure
    -1.01
     ſeveral
    -1.00
     raiſ
    -0.98
     purpoſe
    -0.98
     themſelves
    -0.97
     itſelf
    -0.95
     becauſe
    -0.95
     uſed
    -0.94
    POSITIVE LOGITS
    Oise
    0.65
     journaux
    0.54
     Customization
    0.54
     renseignements
    0.52
    Alsace
    0.51
    encana
    0.50
     spécialistes
    0.50
     télécharge
    0.50
     Overcome
    0.50
    pisah
    0.50
    Activations Density 6.344%

    No Known Activations