© 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. 12510
    Prev
    Next
    INDEX
    Explanations

    Japanese names, movie titles, festivals, and award-related terms

    oai_token-act-pair · gemini-2.0-flash

    Japanese text

    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
     Roskov
    -0.68
    tagHelperRunner
    -0.50
    ként
    -0.47
     CiNii
    -0.46
     autorytatywna
    -0.46
    Demografie
    -0.45
    Jeografia
    -0.45
    #+#
    -0.45
    afficheront
    -0.45
     plantel
    -0.44
    POSITIVE LOGITS
    modelBuilder
    0.58
     Aoki
    0.52
    spiegel
    0.52
     Heere
    0.50
    korean
    0.50
    cillors
    0.49
    AtIndexPath
    0.49
     Alfaro
    0.48
     Decker
    0.48
     Poehler
    0.48
    Activations Density 4.096%

    No Known Activations