© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15823
    Prev
    Next
    INDEX
    Explanations

    the word "theme" and words that immediately follow it

    oai_token-act-pair · gemini-2.0-flash

    theme

    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
     theme
    -1.48
     Theme
    -1.45
    Theme
    -1.39
     themes
    -1.34
    theme
    -1.34
     Themes
    -1.31
     THEME
    -1.30
    Themes
    -1.27
    THEME
    -1.21
    themes
    -1.19
    POSITIVE LOGITS
     Ed
    1.84
     ed
    1.81
     ED
    1.80
    Ed
    1.70
    ED
    1.42
     Eds
    1.39
     eds
    1.22
     EDD
    1.21
     Eddie
    1.20
    Eds
    1.20
    Activations Density 1.468%

    No Known Activations