© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3235
    Prev
    Next
    INDEX
    Explanations

    mentions of injustice and/or discrimination

    oai_token-act-pair · gemini-2.0-flash

    Injustice and discrimination

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     tratta
    -0.62
    Rac
    -0.56
     RAC
    -0.47
     Rac
    -0.46
     Dud
    -0.46
    racism
    -0.46
    rona
    -0.45
     jist
    -0.44
    rx
    -0.44
    knights
    -0.42
    POSITIVE LOGITS
    awtextra
    0.66
    TintMode
    0.63
    BeginContext
    0.62
    UnitTesting
    0.61
    SceneManagement
    0.61
    }();
    0.60
    OrWhiteSpace
    0.59
     Infórmanos
    0.59
    UserScript
    0.58
    وردار
    0.58
    Activations Density 7.754%

    No Known Activations