© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7951
    Prev
    Next
    INDEX
    Explanations

    descriptive language about nature, especially geological formations and their appearance due to light and water

    oai_token-act-pair · gemini-2.0-flash

    creating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tagext
    -0.82
    StoryboardSegue
    -0.67
    脚注の使い方
    -0.59
     дописавши
    -0.59
     autorytatywna
    -0.58
     Désolé
    -0.57
     colspan
    -0.54
    Cyfeiriadau
    -0.54
    #+#
    -0.54
    Personendaten
    -0.53
    POSITIVE LOGITS
     HasFactory
    0.61
    بوابة
    0.56
    nonatomic
    0.52
    mappedBy
    0.50
    qrstuvwxyz
    0.49
    datable
    0.47
    tabular
    0.46
     BorderSide
    0.46
    OuterClass
    0.45
     ComVisible
    0.43
    Activations Density 4.377%

    No Known Activations