© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3247
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a lack of specific knowledge or importance

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     käyttö
    -0.50
     aegis
    -0.50
    DataGridView
    -0.49
     quies
    -0.49
     reference
    -0.48
     perkara
    -0.48
     wezen
    -0.48
     reply
    -0.47
    twimg
    -0.47
     parlour
    -0.46
    POSITIVE LOGITS
     محفوظة
    0.82
     whatever
    0.77
    Whatever
    0.74
    enderror
    0.73
     Whatever
    0.70
     regardless
    0.70
    tagHelperRunner
    0.70
    regardless
    0.68
    ActionCreators
    0.68
    GIVEREF
    0.67
    Activations Density 0.837%

    No Known Activations