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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6791
    Prev
    Next
    INDEX
    Explanations

    mentions of groups, laws, organizations, or rules

    oai_token-act-pair · gemini-2.0-flash

    terms related to bans and exclusions

    np_token-act-pair-logits · gpt-4o-mini

    banning related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    prefixer
    -0.65
    StoryboardSegue
    -0.62
     Änder
    -0.56
    IUrlHelper
    -0.55
    ViewFeatures
    -0.54
     CanadaChoose
    -0.52
    straßen
    -0.51
     AssemblyProduct
    -0.51
    EndInit
    -0.51
    HtmlAttribute
    -0.51
    POSITIVE LOGITS
     ban
    0.98
     black
    0.91
    Ban
    0.91
    ban
    0.88
     Ban
    0.87
     banning
    0.82
     suspension
    0.79
     exclusion
    0.79
    black
    0.77
    san
    0.77
    Activations Density 2.933%

    No Known Activations