© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7713
    Prev
    Next
    INDEX
    Explanations

    words related to potential threats or warnings

    oai_token-act-pair · gemini-2.0-flash

    warning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     warning
    -2.56
     Warning
    -2.27
     warnings
    -2.20
     warn
    -2.14
    Warning
    -2.03
    warning
    -2.02
     warned
    -1.97
     warns
    -1.87
     WARNING
    -1.84
     Warnings
    -1.82
    POSITIVE LOGITS
    XmlAccessType
    0.82
    
    0.82
    évaluateur
    0.77
     مشين
    0.63
    athione
    0.61
    abestanden
    0.61
    brainly
    0.59
     للاسماء
    0.59
     esternos
    0.58
    Jeografia
    0.57
    Activations Density 3.847%

    No Known Activations