© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10062
    Prev
    Next
    INDEX
    Explanations

    words related to music events such as concerts and festivals, especially the descriptions of songs for live performance.

    oai_token-act-pair · gemini-2.0-flash

    concert and festival events

    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
    Negative Logits
     live
    -0.67
    live
    -0.61
    Live
    -0.58
     Live
    -0.57
    RenderAtEndOf
    -0.55
    WriteBarrier
    -0.54
     photocopying
    -0.54
     Roskov
    -0.54
     lenker
    -0.54
    LIVE
    -0.53
    POSITIVE LOGITS
    libft
    0.58
    soort
    0.51
    msgTypes
    0.48
     netts
    0.46
     RY
    0.46
    oneg
    0.45
    URLEncoder
    0.44
     head
    0.44
    Charsets
    0.43
     للمعارف
    0.43
    Activations Density 1.554%

    No Known Activations