© 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. 13371
    Prev
    Next
    INDEX
    Explanations

    html tags

    oai_token-act-pair · gemini-2.0-flash

    HTML closing tag

    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
     converging
    -0.55
     visualizing
    -0.52
    vedať
    -0.52
     caseros
    -0.51
     retraction
    -0.50
     perceiving
    -0.50
     realising
    -0.50
     domestiques
    -0.50
     covenants
    -0.50
     veda
    -0.50
    POSITIVE LOGITS
    twimg
    0.68
    sidemargin
    0.67
    SequentialGroup
    0.66
    sweetalert
    0.63
    serviceWorker
    0.63
    MemoryWarning
    0.62
    onActivityResult
    0.61
     gynhyrchwyd
    0.58
    jooq
    0.57
    FailureListener
    0.55
    Activations Density 4.165%

    No Known Activations