© 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. 37984
    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
    ↵
    0.80
    end
    0.78
    nd
    0.77
    mark
    0.71
    sure
    0.71
    ゴ
    0.70
    ators
    0.69
    run
    0.68
    eria
    0.68
    rs
    0.67
    POSITIVE LOGITS
     extrait
    0.77
    REETYPE
    0.77
    PTMR
    0.75
     conversar
    0.74
    θέ
    0.73
     ​​​​
    0.72
     अनलि
    0.71
    anwhile
    0.70
    ILTON
    0.70
     Вме
    0.68
    Activations Density 0.000%

    No Known Activations