© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13123
    Prev
    Next
    INDEX
    Explanations

    scientific publication references, including volume, number, and page numbers

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Monfieur
    -1.20
     Efq
    -1.12
     للاسماء
    -1.10
     myſelf
    -1.09
     ExecuteAsync
    -1.05
     $_"
    -1.02
     itſelf
    -1.02
     poffe
    -1.01
     NUKAT
    -0.99
     Jefus
    -0.98
    POSITIVE LOGITS
     p
    0.45
     
    0.40
     un
    0.38
     P
    0.38
     to
    0.36
      
    0.34
     in
    0.33
    2
    0.33
    許
    0.32
     el
    0.30
    Activations Density 1.980%

    No Known Activations