© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12543
    Prev
    Next
    INDEX
    Explanations

    words/phrases relating to discrimination, prejudice and being an outsider

    oai_token-act-pair · gemini-2.0-flash

    bigotry, prejudice, injustice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    MigrationBuilder
    -0.60
    PostExecute
    -0.56
    TagMode
    -0.56
     esternos
    -0.53
    ungalows
    -0.53
     мәкал
    -0.51
    UnusedPrivate
    -0.49
     Vrbo
    -0.49
    GEBURTSDATUM
    -0.49
     feroit
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.74
     promoted
    0.56
     JADX
    0.52
     perpetuated
    0.51
     disguised
    0.50
    sidemargin
    0.49
    StoredProcedure
    0.48
     inducing
    0.48
    VideoCapture
    0.47
     masquer
    0.47
    Activations Density 8.955%

    No Known Activations