© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10511
    Prev
    Next
    INDEX
    Explanations

    language discussing injustice and marginalized groups in society

    oai_token-act-pair · gemini-2.0-flash

    Social justice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     "','
    -0.75
    intios
    -0.63
     CreateTagHelper
    -0.62
     Alle
    -0.61
    setof
    -0.61
    UserScript
    -0.59
     Aler
    -0.59
     AssemblyCompany
    -0.58
    cellation
    -0.56
     Савезне
    -0.56
    POSITIVE LOGITS
     able
    0.97
     Able
    0.73
    Able
    0.60
     schop
    0.59
     ability
    0.57
    able
    0.55
     capaces
    0.52
    
    0.46
     capaz
    0.45
    ABILITY
    0.43
    Activations Density 3.158%

    No Known Activations