© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4364
    Prev
    Next
    INDEX
    Explanations

    calls to action or commands

    oai_token-act-pair · gemini-2.0-flash

    go/come

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     disambiguazione
    -0.69
    }],
    -0.66
     prochaines
    -0.64
    İstinadlar
    -0.63
     avoient
    -0.63
    kloped
    -0.63
    GEBURTSDATUM
    -0.62
     couverte
    -0.61
    Geplaatst
    -0.61
    IUrlHelper
    -0.59
    POSITIVE LOGITS
     take
    0.83
     get
    0.83
     find
    0.80
     consider
    0.77
     participate
    0.74
     eat
    0.73
     play
    0.73
     conduct
    0.72
     make
    0.72
     try
    0.70
    Activations Density 0.561%

    No Known Activations