© 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. 12-GEMMASCOPE-2-RES-262K
    7. 30774
    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
     chord
    0.64
     vectorized
    0.64
    ρικ
    0.64
     <<"
    0.63
     =",
    0.63
     {:.
    0.62
     식으로
    0.62
     Normalized
    0.62
    |-\
    0.62
     лежит
    0.62
    POSITIVE LOGITS
    Other
    1.05
    Об
    0.90
    OTHER
    0.81
    zial
    0.81
    Anche
    0.80
    Oste
    0.80
    Nonce
    0.79
    Def
    0.77
    Funeral
    0.77
    Aud
    0.77
    Activations Density 0.000%

    No Known Activations