© 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. 10910
    Prev
    Next
    INDEX
    Explanations

    language related to right-wing politics, hate speech, and political commentary

    oai_token-act-pair · gemini-2.0-flash

    Right-wing politics and racism

    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
    parsedMessage
    -0.63
    fjspx
    -0.59
    itecture
    -0.56
    oredCriteria
    -0.52
    AnchorStyles
    -0.52
    }$​
    -0.51
    addContainerGap
    -0.51
    Abr
    -0.49
     betting
    -0.48
     funt
    -0.48
    POSITIVE LOGITS
    PMailer
    0.59
     big
    0.57
    Eksterne
    0.52
     članak
    0.51
    šinou
    0.50
    big
    0.50
    ConstraintMaker
    0.47
    вобо
    0.46
     free
    0.46
    RequestMethod
    0.46
    Activations Density 2.679%

    No Known Activations