© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2928
    Prev
    Next
    INDEX
    Explanations

    words associated with leadership roles in organizations and committees.

    oai_token-act-pair · gemini-2.0-flash

    chair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     chair
    -1.18
     Chair
    -1.16
    Chair
    -1.15
    chair
    -1.05
     Chairman
    -0.98
    Chairman
    -0.96
     chairman
    -0.94
     Chairperson
    -0.91
     Chairs
    -0.88
     chairperson
    -0.88
    POSITIVE LOGITS
    stdafx
    0.66
    anxi
    0.54
    },{
    0.54
    parently
    0.54
    ixe
    0.52
    łgorzata
    0.52
    არი
    0.52
    APOLIS
    0.51
    })));
    0.51
     vertical
    0.50
    Activations Density 9.311%

    No Known Activations