© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16225
    Prev
    Next
    INDEX
    Explanations

    words that are a negative affect on a system, such as bugs, problems, fixes, hacks, and so on.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    .
    -0.47
    ,
    -0.47
    (
    -0.41
    brigens
    -0.41
    leyen
    -0.39
    isAlive
    -0.39
    fromLTRB
    -0.39
    "
    -0.39
    ين
    -0.38
     
    -0.37
    POSITIVE LOGITS
     مرئيه
    0.98
    <bos>
    0.96
     Мексичка
    0.89
     betweenstory
    0.83
    }{*}{
    0.82
    adpleegd
    0.77
    Aholisi
    0.74
    betic
    0.72
    RegressionTest
    0.72
     nakalista
    0.72
    Activations Density 69.298%

    No Known Activations