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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2516
    Prev
    Next
    INDEX
    Explanations

    Japanese text/characters.

    oai_token-act-pair · gemini-2.0-flash

    Multiple/Foreign Languages/Japanese

    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
     Abonnez
    -0.66
    SharedDtor
    -0.54
    iettivo
    -0.49
     coloring
    -0.48
     AttributeSet
    -0.48
     truss
    -0.48
    ItemBackground
    -0.48
     CWE
    -0.47
     onCancelled
    -0.47
    踐
    -0.47
    POSITIVE LOGITS
     zvuky
    0.61
    findpost
    0.59
    ="@+
    0.52
    umably
    0.52
     rajut
    0.51
    setVerticalGroup
    0.50
    kolwiek
    0.50
    jsdelivr
    0.50
     @"/
    0.49
     wireType
    0.48
    Activations Density 0.101%

    No Known Activations