© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7220
    Prev
    Next
    INDEX
    Explanations

    a series of words frequently appearing in a music review, such as "band", "single", "album", "recorded", and band member titles

    oai_token-act-pair · gemini-2.0-flash

    musical groups

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Wiktionnaire
    -0.55
    őtt
    -0.53
    ResumeLayout
    -0.48
    ⇌
    -0.48
    RDP
    -0.47
     posibil
    -0.46
    ukh
    -0.44
    shadowOpacity
    -0.43
     macchina
    -0.43
     dis
    -0.43
    POSITIVE LOGITS
    UpInside
    0.82
     oprot
    0.73
    ScopeManager
    0.65
     تانيه
    0.62
    mergeFrom
    0.60
    :✨
    0.60
    %")
    0.59
    ()};
    0.58
    homonymie
    0.56
    Bakgrunnsstoff
    0.56
    Activations Density 0.267%

    No Known Activations