© 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. 12747
    Prev
    Next
    INDEX
    Explanations

    instances of obligation or advice denoted by "must" and passive voice verbs, sometimes including surrounding context.

    oai_token-act-pair · gemini-2.0-flash

    must

    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
    should
    -0.77
    must
    -0.71
    Should
    -0.71
     Should
    -0.67
    Must
    -0.67
     должна
    -0.61
     doivent
    -0.61
     должны
    -0.60
     fhould
    -0.60
     Debe
    -0.60
    POSITIVE LOGITS
     inspect
    0.80
     develop
    0.78
     acquire
    0.77
     investigate
    0.77
     teach
    0.75
     distribute
    0.75
     fulfill
    0.73
     organize
    0.73
     learn
    0.73
     ensure
    0.73
    Activations Density 4.665%

    No Known Activations