© 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. 1850
    Prev
    Next
    INDEX
    Explanations

    chemical suffixes and XML tags

    oai_token-act-pair · gemini-2.0-flash

    Non-English 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
     PACE
    -0.97
    MCE
    -0.88
     ACE
    -0.88
     Vance
    -0.85
     Bale
    -0.84
     Tole
    -0.82
     Mase
    -0.81
    ACE
    -0.81
    PACE
    -0.79
     Lame
    -0.79
    POSITIVE LOGITS
     amitié
    0.67
     réflexion
    0.67
     réputation
    0.59
     circonst
    0.56
    wikk
    0.49
     leçon
    0.48
     faculté
    0.47
    Descripció
    0.47
     braccia
    0.46
    Attrs
    0.46
    Activations Density 1.206%

    No Known Activations