© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16134
    Prev
    Next
    INDEX
    Explanations

    words/phrases related to music production (song, album, band, etc.)

    oai_token-act-pair · gemini-2.0-flash

    Bands and music

    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
    Negative Logits
    awtextra
    -0.60
    Попис
    -0.59
     Combien
    -0.56
    isatie
    -0.53
    DropColumn
    -0.52
    principalColumn
    -0.52
     препратки
    -0.52
     János
    -0.52
    SBATCH
    -0.50
     BitmapFactory
    -0.50
    POSITIVE LOGITS
    enumi
    0.60
     незавершена
    0.52
    brido
    0.52
     okuyayım
    0.52
    EndContext
    0.49
     genre
    0.48
     piratas
    0.47
     rospy
    0.47
    PhysRev
    0.47
    PointerException
    0.47
    Activations Density 2.535%

    No Known Activations