© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9581
    Prev
    Next
    INDEX
    Explanations

    language related to negative emotions and personal failings

    oai_token-act-pair · gemini-2.0-flash

    failure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    body
    -0.41
     mas
    -0.40
    app
    -0.39
    if
    -0.38
    of
    -0.38
     yat
    -0.38
     body
    -0.37
    身
    -0.37
     se
    -0.37
    LayoutConstraint
    -0.37
    POSITIVE LOGITS
    WithIOException
    0.88
     myſelf
    0.87
     itſelf
    0.87
    SourceChecksum
    0.84
     Majefty
    0.83
    AndroidJUnit
    0.82
     InputDecoration
    0.82
     Monfieur
    0.82
     Anſ
    0.82
    HasAnnotation
    0.80
    Activations Density 0.544%

    No Known Activations