© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1851
    Prev
    Next
    INDEX
    Explanations

    discussion of political crimes and legal processes

    oai_token-act-pair · gemini-2.0-flash

    multi-part political statements

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

    legal context

    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
    Personendaten
    -0.55
     Rast
    -0.45
    rast
    -0.41
    Rast
    -0.39
     tra
    -0.38
     Huy
    -0.38
    JUDGE
    -0.38
    idir
    -0.38
     intptr
    -0.37
     Front
    -0.37
    POSITIVE LOGITS
    IsContent
    0.89
     MessageBoxIcon
    0.81
     FontWeight
    0.80
    AddTagHelper
    0.77
    Naissance
    0.71
    posedge
    0.71
    ękuję
    0.69
     initComponents
    0.68
    ंदीखरीदारी
    0.67
    ofire
    0.66
    Activations Density 0.841%

    No Known Activations