© 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. 11528
    Prev
    Next
    INDEX
    Explanations

    generally positive adjectives and qualifying nouns.

    oai_token-act-pair · gemini-2.0-flash

    Broad reports and opinions

    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
    .
    -0.57
     consistently
    -0.55
     measures
    -0.54
     precisely
    -0.54
     of
    -0.52
     thoroughly
    -0.52
     essentially
    -0.52
     seemingly
    -0.51
     generally
    -0.51
     reported
    -0.50
    POSITIVE LOGITS
    sizeCache
    0.73
     avoient
    0.73
     feroit
    0.71
     normaux
    0.69
     peuples
    0.69
     fermés
    0.68
     aktivitet
    0.68
     dieux
    0.68
     auroit
    0.68
     étoit
    0.67
    Activations Density 15.105%

    No Known Activations