© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4965
    Prev
    Next
    INDEX
    Explanations

    words associated with sounds with a negative connotation

    oai_token-act-pair · gemini-2.0-flash

    sounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.55
    stree
    -0.49
     Reconciliation
    -0.48
    UNSIGNED
    -0.48
    Reprodu
    -0.42
     retry
    -0.42
    recon
    -0.41
    abetes
    -0.40
    Blink
    -0.40
     pues
    -0.40
    POSITIVE LOGITS
    clat
    0.73
    WriteBarrier
    0.73
     pleaſure
    0.67
    ̍t
    0.66
     fanfare
    0.63
     Monfieur
    0.61
    IntoConstraints
    0.60
     themſelves
    0.59
     pomp
    0.59
     ſmall
    0.58
    Activations Density 1.438%

    No Known Activations