© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6503
    Prev
    Next
    INDEX
    Explanations

    sentences about a corporate executive's roles and responsibilities within a company

    oai_token-act-pair · gemini-2.0-flash

    responsible

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     समीक्षाओं
    -0.62
    setVerticalGroup
    -0.61
    GOTREF
    -0.56
    ⓘ
    -0.56
    speakers
    -0.55
    MMV
    -0.48
     prêtres
    -0.48
    umbres
    -0.47
    oolean
    -0.47
    ристання
    -0.47
    POSITIVE LOGITS
     responsibility
    1.66
     responsible
    1.60
     Responsible
    1.50
    Responsible
    1.46
     Responsibility
    1.45
    responsible
    1.42
    responsibility
    1.41
     RESPONS
    1.38
     respon
    1.30
    Responsibility
    1.30
    Activations Density 1.769%

    No Known Activations