© 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-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 16188
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    řen
    0.90
    verages
    0.80
    처럼
    0.80
    响起
    0.78
     democrat
    0.76
    nagar
    0.76
    тический
    0.76
    檛
    0.76
    ţia
    0.74
    ācijas
    0.73
    POSITIVE LOGITS
    ба
    0.71
    ग
    0.70
     denke
    0.68
    ఞ
    0.68
     trouvent
    0.66
    Cape
    0.64
    ००
    0.63
     It
    0.63
    cape
    0.62
    عداد
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.