© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7260
    Prev
    Next
    INDEX
    Explanations

    this neuron is looking for film directors and seemingly random code snippets

    oai_token-act-pair · gemini-2.0-flash

    directory paths

    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
     director
    -2.66
     directors
    -2.61
     Director
    -2.45
     Directors
    -2.42
    Director
    -2.42
    director
    -2.33
    Directors
    -2.28
     DIRECTOR
    -2.23
    directors
    -2.19
     directed
    -2.14
    POSITIVE LOGITS
    agramm
    0.53
     chi̍t
    0.52
     respeito
    0.44
    rachtet
    0.43
    Vidite
    0.41
    Rune
    0.41
     Immune
    0.41
     immu
    0.41
    aryti
    0.41
    insee
    0.41
    Activations Density 1.854%

    No Known Activations