© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3667
    Prev
    Next
    INDEX
    Explanations

    references to LGBTQ+ topics, particularly in media and culture

    oai_token-act-pair · gemini-2.0-flash

    terms related to drag culture

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

    drag/ LGBTQ+/media/celebrities

    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
    AxisAlignment
    -0.60
    UnknownFieldSet
    -0.50
     simpto
    -0.49
    ViewImports
    -0.48
     AttributeSet
    -0.48
    CppCodeGen
    -0.48
    ⓧ
    -0.48
    thmus
    -0.48
    orship
    -0.48
    coration
    -0.48
    POSITIVE LOGITS
    oa̍t
    0.74
     drag
    0.65
    
    0.61
     Ru
    0.60
     page
    0.58
    SharedDtor
    0.57
    Przypisy
    0.55
    帖最后由
    0.55
    rupa
    0.54
     cherchés
    0.53
    Activations Density 1.243%

    No Known Activations