© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11903
    Prev
    Next
    INDEX
    Explanations

    strings that contain words like "the", "to", "theme", "chapter", "interesting", and "topic."

    oai_token-act-pair · gemini-2.0-flash

    diverse topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     theme
    -2.61
     Topic
    -2.45
     themes
    -2.45
     Theme
    -2.44
     topic
    -2.42
    Topic
    -2.33
     topics
    -2.28
     Themes
    -2.28
    Theme
    -2.28
     Topics
    -2.22
    POSITIVE LOGITS
     Bennett
    0.50
    Bennett
    0.47
     rhestr
    0.45
    calyp
    0.44
     bicarbon
    0.43
    AfterViewInit
    0.43
     CascadeType
    0.42
     distributed
    0.40
     Bene
    0.40
    ombic
    0.39
    Activations Density 1.139%

    No Known Activations