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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8956
    Prev
    Next
    INDEX
    Explanations

    the word "media."

    oai_token-act-pair · gemini-2.0-flash

    media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     media
    -2.86
     Media
    -2.72
    Media
    -2.69
    media
    -2.56
     MEDIA
    -2.50
    MEDIA
    -2.19
     Medien
    -1.89
    媒体
    -1.85
     medias
    -1.73
     medier
    -1.72
    POSITIVE LOGITS
    Matching
    0.47
     ál
    0.45
     OMITBAD
    0.42
     dessins
    0.41
    matching
    0.40
     mistrzost
    0.40
    brett
    0.40
    Divine
    0.40
     Matching
    0.40
     kema
    0.39
    Activations Density 1.104%

    No Known Activations