© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4813
    Prev
    Next
    INDEX
    Explanations

    language regarding politics, surveys, and marriage equality in Australia

    oai_token-act-pair · gemini-2.0-flash

    Australian-related terms

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

    Australia

    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
    #+#
    -0.79
     ModelExpression
    -0.78
    PhysRev
    -0.78
    +#+
    -0.68
    IsMutable
    -0.66
     Ammon
    -0.66
    ConstraintMaker
    -0.64
    /**
    -0.63
    ingeki
    -0.60
    inSlope
    -0.60
    POSITIVE LOGITS
     Australian
    0.46
    Carriera
    0.45
     Curt
    0.44
     ostavi
    0.44
    arr
    0.43
     Commonwealth
    0.42
     Australia
    0.41
     στιγ
    0.41
    psa
    0.41
     inter
    0.40
    Activations Density 0.550%

    No Known Activations