© 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. 12572
    Prev
    Next
    INDEX
    Explanations

    code documentation, code snippets, and examples in the text

    oai_token-act-pair · gemini-2.0-flash

    code and data structures

    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
     age
    -1.07
     strength
    -1.05
     intensity
    -1.03
     value
    -1.00
     time
    -0.99
     length
    -0.98
     size
    -0.96
     depth
    -0.95
     width
    -0.94
     height
    -0.94
    POSITIVE LOGITS
     syndicated
    0.53
     reprints
    0.53
     calculators
    0.52
     multicast
    0.52
     documentaries
    0.51
     catalogs
    0.51
     distill
    0.51
     cookbook
    0.51
     comics
    0.51
     podcast
    0.51
    Activations Density 8.443%

    No Known Activations