© 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. 11024
    Prev
    Next
    INDEX
    Explanations

    code snippets written in various programming languages.

    oai_token-act-pair · gemini-2.0-flash

    brackets

    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
     ་་
    -1.01
     tenements
    -0.93
     photolibrary
    -0.89
     Esatti
    -0.89
     homeward
    -0.86
     EEU
    -0.86
     timelapse
    -0.85
     skulls
    -0.85
     blest
    -0.85
     Ecclesiastical
    -0.85
    POSITIVE LOGITS
     f
    0.30
     new
    0.27
     t
    0.24
     if
    0.23
     control
    0.22
     file
    0.21
     (
    0.21
     v
    0.21
     self
    0.21
     
    0.21
    Activations Density 22.085%

    No Known Activations