© 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-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201506
    Prev
    Next
    INDEX
    Explanations

    public class MonoBehaviour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_l0_small_affine
    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
    OL
    0.57
    E
    0.54
    IS
    0.52
    ли
    0.51
    Е
    0.51
    𝐔
    0.50
    را
    0.50
    Э
    0.50
    비스
    0.49
    IUM
    0.49
    POSITIVE LOGITS
     Осо
    0.57
     enzimas
    0.53
     PRP
    0.52
    omics
    0.52
     படி
    0.52
     Decision
    0.50
     divorce
    0.50
     Coronation
    0.49
     War
    0.49
    nale
    0.49
    Activations Density 0.001%

    No Known Activations