© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2685
    Prev
    Next
    INDEX
    Explanations

    mentions of certain political figures and hate groups

    oai_token-act-pair · gemini-2.0-flash

    terms associated with racism and white supremacy

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

    Racism or far-right politics

    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
     geslacht
    -0.53
    phosa
    -0.51
    acterium
    -0.50
    astéroïdes
    -0.50
     Rigby
    -0.50
    hoea
    -0.48
    ynchrotron
    -0.48
    maj
    -0.47
     orgasm
    -0.47
    horesis
    -0.47
    POSITIVE LOGITS
     far
    0.81
     neo
    0.75
    +#+#
    0.68
    far
    0.68
     white
    0.67
     Neo
    0.65
    DataAnnotations
    0.63
    awtextra
    0.62
    AddTagHelper
    0.61
    ThroughAttribute
    0.60
    Activations Density 2.421%

    No Known Activations