© 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. 10963
    Prev
    Next
    INDEX
    Explanations

    mentions of conspiracy theories and the use of social media to spread misinformation

    oai_token-act-pair · gemini-2.0-flash

    Political posts

    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
     referenties
    -0.69
    AlterField
    -0.66
    ValueStyle
    -0.61
     Bioaccumulative
    -0.58
     Italijani
    -0.56
     CanadaChoose
    -0.52
     itinéraires
    -0.50
    InitVars
    -0.50
    agisse
    -0.50
    ItemBackground
    -0.49
    POSITIVE LOGITS
     political
    0.58
     insuffisamment
    0.57
    GOTREF
    0.53
     anti
    0.51
     posts
    0.50
     shares
    0.50
     memer
    0.50
     memes
    0.49
     impo
    0.49
    ณา
    0.48
    Activations Density 8.945%

    No Known Activations