© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1646
    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_12_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
    𝓎
    1.77
     permettre
    1.64
    стика
    1.63
    𝐋
    1.61
    𝓂
    1.59
     deportivo
    1.57
    ック
    1.55
    PERATURE
    1.50
     vitesses
    1.50
     destinados
    1.48
    POSITIVE LOGITS
    yyyy
    1.77
    ll
    1.76
    ment
    1.63
    s
    1.63
    fur
    1.58
    ng
    1.51
    re
    1.50
    {~
    1.45
    ne
    1.44
    ung
    1.42
    Activations Density 0.002%

    No Known Activations