© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11918
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is asking for or offering help

    oai_token-act-pair · gemini-2.0-flash

    variations of "help"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    offsetof
    -0.56
    Datuak
    -0.54
    djangoproject
    -0.47
    HtmlAttribute
    -0.46
    rofoam
    -0.44
    opedic
    -0.44
    neux
    -0.41
    iastes
    -0.41
    edish
    -0.40
    AtIndexPath
    -0.40
    POSITIVE LOGITS
     help
    2.97
    help
    2.77
    Help
    2.70
     Help
    2.69
     helping
    2.61
     helped
    2.52
     helps
    2.50
     HELP
    2.42
    helped
    2.39
     Helps
    2.31
    Activations Density 5.937%

    No Known Activations