© 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. 11750
    Prev
    Next
    INDEX
    Explanations

    category and list dividers, specifically when they are a colon preceded by a short string of letters

    oai_token-act-pair · gemini-2.0-flash

    Code and mixed language text

    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
     for
    -0.64
     
    -0.48
     with
    -0.48
     «
    -0.45
     y
    -0.45
     G
    -0.45
     Y
    -0.45
     I
    -0.45
     "
    -0.44
     is
    -0.44
    POSITIVE LOGITS
     itſelf
    1.34
     myſelf
    1.33
     Jefus
    1.29
     ―――――
    1.27
     purpoſe
    1.23
     pleaſure
    1.22
     Monfieur
    1.20
     ſever
    1.17
     ſche
    1.17
    ſelf
    1.14
    Activations Density 2.271%

    No Known Activations