© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 266
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     benötigen
    0.63
     trenger
    0.59
     effectué
    0.57
     varient
    0.55
    ៕
    0.55
     quantité
    0.54
     bevat
    0.54
     soorten
    0.54
     sorgt
    0.53
     crab
    0.52
    POSITIVE LOGITS
    B
    0.84
    J
    0.77
    Conta
    0.77
    Results
    0.76
    U
    0.75
    Result
    0.75
    Random
    0.75
    Item
    0.74
    Representation
    0.73
    Ocean
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.